Daily Papers

With the rapid popularity of large language models such as ChatGPT and GPT-4, a growing amount of attention is paid to their safety concerns. These models may generate insulting and discriminatory content, reflect incorrect social values, and may be used for malicious purposes such as fraud and dissemination of misleading information. Evaluating and enhancing their safety is particularly essential for the wide application of large language models (LLMs). To further promote the safe deployment of LLMs, we develop a Chinese LLM safety assessment benchmark. Our benchmark explores the comprehensive safety performance of LLMs from two perspectives: 8 kinds of typical safety scenarios and 6 types of more challenging instruction attacks. Our benchmark is based on a straightforward process in which it provides the test prompts and evaluates the safety of the generated responses from the evaluated model. In evaluation, we utilize the LLM's strong evaluation ability and develop it as a safety evaluator by prompting. On top of this benchmark, we conduct safety assessments and analyze 15 LLMs including the OpenAI GPT series and other well-known Chinese LLMs, where we observe some interesting findings. For example, we find that instruction attacks are more likely to expose safety issues of all LLMs. Moreover, to promote the development and deployment of safe, responsible, and ethical AI, we publicly release SafetyPrompts including 100k augmented prompts and responses by LLMs.

The rapid development of large reasoning models, such as OpenAI-o3 and DeepSeek-R1, has led to significant improvements in complex reasoning over non-reasoning large language models~(LLMs). However, their enhanced capabilities, combined with the open-source access of models like DeepSeek-R1, raise serious safety concerns, particularly regarding their potential for misuse. In this work, we present a comprehensive safety assessment of these reasoning models, leveraging established safety benchmarks to evaluate their compliance with safety regulations. Furthermore, we investigate their susceptibility to adversarial attacks, such as jailbreaking and prompt injection, to assess their robustness in real-world applications. Through our multi-faceted analysis, we uncover four key findings: (1) There is a significant safety gap between the open-source R1 models and the o3-mini model, on both safety benchmark and attack, suggesting more safety effort on R1 is needed. (2) The distilled reasoning model shows poorer safety performance compared to its safety-aligned base models. (3) The stronger the model's reasoning ability, the greater the potential harm it may cause when answering unsafe questions. (4) The thinking process in R1 models pose greater safety concerns than their final answers. Our study provides insights into the security implications of reasoning models and highlights the need for further advancements in R1 models' safety to close the gap.

Large Reasoning Models (LRMs) improve answer quality through explicit chain-of-thought, yet this very capability introduces new safety risks: harmful content can be subtly injected, surface gradually, or be justified by misleading rationales within the reasoning trace. Existing safety evaluations, however, primarily focus on output-level judgments and rarely capture these dynamic risks along the reasoning process. In this paper, we present SafeRBench, the first benchmark that assesses LRM safety end-to-end -- from inputs and intermediate reasoning to final outputs. (1) Input Characterization: We pioneer the incorporation of risk categories and levels into input design, explicitly accounting for affected groups and severity, and thereby establish a balanced prompt suite reflecting diverse harm gradients. (2) Fine-Grained Output Analysis: We introduce a micro-thought chunking mechanism to segment long reasoning traces into semantically coherent units, enabling fine-grained evaluation across ten safety dimensions. (3) Human Safety Alignment: We validate LLM-based evaluations against human annotations specifically designed to capture safety judgments. Evaluations on 19 LRMs demonstrate that SafeRBench enables detailed, multidimensional safety assessment, offering insights into risks and protective mechanisms from multiple perspectives.

We introduce LlavaGuard, a family of VLM-based safeguard models, offering a versatile framework for evaluating the safety compliance of visual content. Specifically, we designed LlavaGuard for dataset annotation and generative model safeguarding. To this end, we collected and annotated a high-quality visual dataset incorporating a broad safety taxonomy, which we use to tune VLMs on context-aware safety risks. As a key innovation, LlavaGuard's new responses contain comprehensive information, including a safety rating, the violated safety categories, and an in-depth rationale. Further, our introduced customizable taxonomy categories enable the context-specific alignment of LlavaGuard to various scenarios. Our experiments highlight the capabilities of LlavaGuard in complex and real-world applications. We provide checkpoints ranging from 7B to 34B parameters demonstrating state-of-the-art performance, with even the smallest models outperforming baselines like GPT-4. We make our dataset and model weights publicly available and invite further research to address the diverse needs of communities and contexts.

This technical report provides a detailed overview of Endoscapes, a dataset of laparoscopic cholecystectomy (LC) videos with highly intricate annotations targeted at automated assessment of the Critical View of Safety (CVS). Endoscapes comprises 201 LC videos with frames annotated sparsely but regularly with segmentation masks, bounding boxes, and CVS assessment by three different clinical experts. Altogether, there are 11090 frames annotated with CVS and 1933 frames annotated with tool and anatomy bounding boxes from the 201 videos, as well as an additional 422 frames from 50 of the 201 videos annotated with tool and anatomy segmentation masks. In this report, we provide detailed dataset statistics (size, class distribution, dataset splits, etc.) and a comprehensive performance benchmark for instance segmentation, object detection, and CVS prediction. The dataset and model checkpoints are publically available at https://github.com/CAMMA-public/Endoscapes.

Current Vision Language Models (VLMs) remain vulnerable to malicious prompts that induce harmful outputs. Existing safety benchmarks for VLMs primarily rely on automated evaluation methods, but these methods struggle to detect implicit harmful content or produce inaccurate evaluations. Therefore, we found that existing benchmarks have low levels of harmfulness, ambiguous data, and limited diversity in image-text pair combinations. To address these issues, we propose the ELITE benchmark, a high-quality safety evaluation benchmark for VLMs, underpinned by our enhanced evaluation method, the ELITE evaluator. The ELITE evaluator explicitly incorporates a toxicity score to accurately assess harmfulness in multimodal contexts, where VLMs often provide specific, convincing, but unharmful descriptions of images. We filter out ambiguous and low-quality image-text pairs from existing benchmarks using the ELITE evaluator and generate diverse combinations of safe and unsafe image-text pairs. Our experiments demonstrate that the ELITE evaluator achieves superior alignment with human evaluations compared to prior automated methods, and the ELITE benchmark offers enhanced benchmark quality and diversity. By introducing ELITE, we pave the way for safer, more robust VLMs, contributing essential tools for evaluating and mitigating safety risks in real-world applications.

Foundation models are routinely fine-tuned for use in particular domains, yet safety assessments are typically conducted only on base models, implicitly assuming that safety properties persist through downstream adaptation. We test this assumption by analyzing the safety behavior of 100 models, including widely deployed fine-tunes in the medical and legal domains as well as controlled adaptations of open foundation models alongside their bases. Across general-purpose and domain-specific safety benchmarks, we find that benign fine-tuning induces large, heterogeneous, and often contradictory changes in measured safety: models frequently improve on some instruments while degrading on others, with substantial disagreement across evaluations. These results show that safety behavior is not stable under ordinary downstream adaptation, raising critical questions about governance and deployment practices centered on base-model evaluations. Without explicit re-evaluation of fine-tuned models in deployment-relevant contexts, such approaches fall short of adequately managing downstream risk, overlooking practical sources of harm -- failures that are especially consequential in high-stakes settings and challenge current accountability paradigms.

Recently, the DeepSeek series of models, leveraging their exceptional reasoning capabilities and open-source strategy, is reshaping the global AI landscape. Despite these advantages, they exhibit significant safety deficiencies. Research conducted by Robust Intelligence, a subsidiary of Cisco, in collaboration with the University of Pennsylvania, revealed that DeepSeek-R1 has a 100\% attack success rate when processing harmful prompts. Additionally, multiple safety companies and research institutions have confirmed critical safety vulnerabilities in this model. As models demonstrating robust performance in Chinese and English, DeepSeek models require equally crucial safety assessments in both language contexts. However, current research has predominantly focused on safety evaluations in English environments, leaving a gap in comprehensive assessments of their safety performance in Chinese contexts. In response to this gap, this study introduces CHiSafetyBench, a Chinese-specific safety evaluation benchmark. This benchmark systematically evaluates the safety of DeepSeek-R1 and DeepSeek-V3 in Chinese contexts, revealing their performance across safety categories. The experimental results quantify the deficiencies of these two models in Chinese contexts, providing key insights for subsequent improvements. It should be noted that, despite our efforts to establish a comprehensive, objective, and authoritative evaluation benchmark, the selection of test samples, characteristics of data distribution, and the setting of evaluation criteria may inevitably introduce certain biases into the evaluation results. We will continuously optimize the evaluation benchmark and periodically update this report to provide more comprehensive and accurate assessment outcomes. Please refer to the latest version of the paper for the most recent evaluation results and conclusions.

Vision-language models (VLMs), which process image and text inputs, are increasingly integrated into chat assistants and other consumer AI applications. Without proper safeguards, however, VLMs may give harmful advice (e.g. how to self-harm) or encourage unsafe behaviours (e.g. to consume drugs). Despite these clear hazards, little work so far has evaluated VLM safety and the novel risks created by multimodal inputs. To address this gap, we introduce MSTS, a Multimodal Safety Test Suite for VLMs. MSTS comprises 400 test prompts across 40 fine-grained hazard categories. Each test prompt consists of a text and an image that only in combination reveal their full unsafe meaning. With MSTS, we find clear safety issues in several open VLMs. We also find some VLMs to be safe by accident, meaning that they are safe because they fail to understand even simple test prompts. We translate MSTS into ten languages, showing non-English prompts to increase the rate of unsafe model responses. We also show models to be safer when tested with text only rather than multimodal prompts. Finally, we explore the automation of VLM safety assessments, finding even the best safety classifiers to be lacking.

The rapid evolution of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) has produced substantial gains in reasoning, perception, and generative capability across language and vision. However, whether these advances yield commensurate improvements in safety remains unclear, in part due to fragmented evaluation practices limited to single modalities or threat models. In this report, we present an integrated safety evaluation of 7 frontier models: GPT-5.2, Gemini 3 Pro, Qwen3-VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5. We evaluate each model across language, vision-language, and image generation settings using a unified protocol that integrates benchmark evaluation, adversarial evaluation, multilingual evaluation, and compliance evaluation. Aggregating our evaluations into safety leaderboards and model safety profiles across multiple evaluation modes reveals a sharply heterogeneous safety landscape. While GPT-5.2 demonstrates consistently strong and balanced safety performance across evaluations, other models exhibit pronounced trade-offs among benchmark safety, adversarial alignment, multilingual generalization, and regulatory compliance. Both language and vision-language modalities show significant vulnerability under adversarial evaluation, with all models degrading substantially despite strong results on standard benchmarks. Text-to-image models achieve relatively stronger alignment in regulated visual risk categories, yet remain brittle under adversarial or semantically ambiguous prompts. Overall, these results show that safety in frontier models is inherently multidimensional--shaped by modality, language, and evaluation scheme, underscoring the need for standardized safety evaluations to accurately assess real-world risk and guide responsible model development and deployment.

We present SGuard-v1, a lightweight safety guardrail for Large Language Models (LLMs), which comprises two specialized models to detect harmful content and screen adversarial prompts in human-AI conversational settings. The first component, ContentFilter, is trained to identify safety risks in LLM prompts and responses in accordance with the MLCommons hazard taxonomy, a comprehensive framework for trust and safety assessment of AI. The second component, JailbreakFilter, is trained with a carefully designed curriculum over integrated datasets and findings from prior work on adversarial prompting, covering 60 major attack types while mitigating false-unsafe classification. SGuard-v1 is built on the 2B-parameter Granite-3.3-2B-Instruct model that supports 12 languages. We curate approximately 1.4 million training instances from both collected and synthesized data and perform instruction tuning on the base model, distributing the curated data across the two component according to their designated functions. Through extensive evaluation on public and proprietary safety benchmarks, SGuard-v1 achieves state-of-the-art safety performance while remaining lightweight, thereby reducing deployment overhead. SGuard-v1 also improves interpretability for downstream use by providing multi-class safety predictions and their binary confidence scores. We release the SGuard-v1 under the Apache-2.0 License to enable further research and practical deployment in AI safety.

Large language models (LLMs) have demonstrated remarkable capabilities across various applications, highlighting the urgent need for comprehensive safety evaluations. In particular, the enhanced Chinese language proficiency of LLMs, combined with the unique characteristics and complexity of Chinese expressions, has driven the emergence of Chinese-specific benchmarks for safety assessment. However, these benchmarks generally fall short in effectively exposing LLM safety vulnerabilities. To address the gap, we introduce JailBench, the first comprehensive Chinese benchmark for evaluating deep-seated vulnerabilities in LLMs, featuring a refined hierarchical safety taxonomy tailored to the Chinese context. To improve generation efficiency, we employ a novel Automatic Jailbreak Prompt Engineer (AJPE) framework for JailBench construction, which incorporates jailbreak techniques to enhance assessing effectiveness and leverages LLMs to automatically scale up the dataset through context-learning. The proposed JailBench is extensively evaluated over 13 mainstream LLMs and achieves the highest attack success rate against ChatGPT compared to existing Chinese benchmarks, underscoring its efficacy in identifying latent vulnerabilities in LLMs, as well as illustrating the substantial room for improvement in the security and trustworthiness of LLMs within the Chinese context. Our benchmark is publicly available at https://github.com/STAIR-BUPT/JailBench.

Despite increasing efforts to ensure the safety of large language models (LLMs), most existing safety assessments and moderation tools remain heavily biased toward English and other high-resource languages, leaving majority of global languages underexamined. To address this gap, we introduce a manually annotated benchmark dataset for language model safety classification in Polish. We also create adversarially perturbed variants of these samples designed to challenge model robustness. We conduct a series of experiments to evaluate LLM-based and classifier-based models of varying sizes and architectures. Specifically, we fine-tune three models: Llama-Guard-3-8B, a HerBERT-based classifier (a Polish BERT derivative), and PLLuM, a Polish-adapted Llama-8B model. We train these models using different combinations of annotated data and evaluate their performance, comparing it against publicly available guard models. Results demonstrate that the HerBERT-based classifier achieves the highest overall performance, particularly under adversarial conditions.

Large language models (LLMs) have achieved remarkable capabilities but remain vulnerable to adversarial prompts known as jailbreaks, which can bypass safety alignment and elicit harmful outputs. Despite growing efforts in LLM safety research, existing evaluations are often fragmented, focused on isolated attack or defense techniques, and lack systematic, reproducible analysis. In this work, we introduce PandaGuard, a unified and modular framework that models LLM jailbreak safety as a multi-agent system comprising attackers, defenders, and judges. Our framework implements 19 attack methods and 12 defense mechanisms, along with multiple judgment strategies, all within a flexible plugin architecture supporting diverse LLM interfaces, multiple interaction modes, and configuration-driven experimentation that enhances reproducibility and practical deployment. Built on this framework, we develop PandaBench, a comprehensive benchmark that evaluates the interactions between these attack/defense methods across 49 LLMs and various judgment approaches, requiring over 3 billion tokens to execute. Our extensive evaluation reveals key insights into model vulnerabilities, defense cost-performance trade-offs, and judge consistency. We find that no single defense is optimal across all dimensions and that judge disagreement introduces nontrivial variance in safety assessments. We release the code, configurations, and evaluation results to support transparent and reproducible research in LLM safety.

With the profound development of large language models(LLMs), their safety concerns have garnered increasing attention. However, there is a scarcity of Chinese safety benchmarks for LLMs, and the existing safety taxonomies are inadequate, lacking comprehensive safety detection capabilities in authentic Chinese scenarios. In this work, we introduce CHiSafetyBench, a dedicated safety benchmark for evaluating LLMs' capabilities in identifying risky content and refusing answering risky questions in Chinese contexts. CHiSafetyBench incorporates a dataset that covers a hierarchical Chinese safety taxonomy consisting of 5 risk areas and 31 categories. This dataset comprises two types of tasks: multiple-choice questions and question-answering, evaluating LLMs from the perspectives of risk content identification and the ability to refuse answering risky questions respectively. Utilizing this benchmark, we validate the feasibility of automatic evaluation as a substitute for human evaluation and conduct comprehensive automatic safety assessments on mainstream Chinese LLMs. Our experiments reveal the varying performance of different models across various safety domains, indicating that all models possess considerable potential for improvement in Chinese safety capabilities. Our dataset is publicly available at https://github.com/UnicomAI/UnicomBenchmark/tree/main/CHiSafetyBench.

Search agents connect LLMs to the Internet, enabling access to broader and more up-to-date information. However, unreliable search results may also pose safety threats to end users, establishing a new threat surface. In this work, we conduct two in-the-wild experiments to demonstrate both the prevalence of low-quality search results and their potential to misguide agent behaviors. To counter this threat, we introduce an automated red-teaming framework that is systematic, scalable, and cost-efficient, enabling lightweight and harmless safety assessments of search agents. Building on this framework, we construct the SafeSearch benchmark, which includes 300 test cases covering five categories of risks (e.g., misinformation and indirect prompt injection). Using this benchmark, we evaluate three representative search agent scaffolds, covering search workflow, tool-calling, and deep research, across 7 proprietary and 8 open-source backend LLMs. Our results reveal substantial vulnerabilities of LLM-based search agents: when exposed to unreliable websites, the highest ASR reached 90.5% for GPT-4.1-mini under a search workflow setting. Moreover, our analysis highlights the limited effectiveness of common defense practices, such as reminder prompting. This emphasizes the value of our framework in promoting transparency for safer agent development. Our codebase and test cases are publicly available: https://github.com/jianshuod/SafeSearch.

Recent advancements in Large Language Models (LLMs) have enabled them to approach human-level persuasion capabilities. However, such potential also raises concerns about the safety risks of LLM-driven persuasion, particularly their potential for unethical influence through manipulation, deception, exploitation of vulnerabilities, and many other harmful tactics. In this work, we present a systematic investigation of LLM persuasion safety through two critical aspects: (1) whether LLMs appropriately reject unethical persuasion tasks and avoid unethical strategies during execution, including cases where the initial persuasion goal appears ethically neutral, and (2) how influencing factors like personality traits and external pressures affect their behavior. To this end, we introduce PersuSafety, the first comprehensive framework for the assessment of persuasion safety which consists of three stages, i.e., persuasion scene creation, persuasive conversation simulation, and persuasion safety assessment. PersuSafety covers 6 diverse unethical persuasion topics and 15 common unethical strategies. Through extensive experiments across 8 widely used LLMs, we observe significant safety concerns in most LLMs, including failing to identify harmful persuasion tasks and leveraging various unethical persuasion strategies. Our study calls for more attention to improve safety alignment in progressive and goal-driven conversations such as persuasion.

Large language models (LLMs) are increasingly explored as scalable tools for mental health counseling, yet evaluating their safety remains challenging due to the interactional and context-dependent nature of clinical harm. Existing evaluation frameworks predominantly assess isolated responses using coarse-grained taxonomies or static datasets, limiting their ability to diagnose how harms emerge and accumulate over multi-turn counseling interactions. In this work, we introduce R-MHSafe, a role-aware mental health safety taxonomy that characterizes clinically significant harm in terms of the interactional roles an AI counselor adopts, including perpetrator, instigator, facilitator, or enabler, combined with clinically grounded harm categories. Then, we propose MHSafeEval, a closed-loop, agent-based evaluation framework that formulates safety assessment as trajectory-level discovery of harm through adversarial multi-turn interactions, guided by role-aware modeling. Using R-MHSafe and MHSafeEval, we conduct a large-scale evaluation across state-of-the-art LLMs. Our results reveal substantial role-dependent and cumulative safety failures that are systematically missed by existing static benchmarks, and show that our framework significantly improves failure-mode coverage and diagnostic granularity.

Large Language Models (LLMs) are increasingly employed as automated evaluators to assess the safety of generated content, yet their reliability in this role remains uncertain. This study evaluates a diverse set of 11 LLM judge models across critical safety domains, examining three key aspects: self-consistency in repeated judging tasks, alignment with human judgments, and susceptibility to input artifacts such as apologetic or verbose phrasing. Our findings reveal that biases in LLM judges can significantly distort the final verdict on which content source is safer, undermining the validity of comparative evaluations. Notably, apologetic language artifacts alone can skew evaluator preferences by up to 98\%. Contrary to expectations, larger models do not consistently exhibit greater robustness, while smaller models sometimes show higher resistance to specific artifacts. To mitigate LLM evaluator robustness issues, we investigate jury-based evaluations aggregating decisions from multiple models. Although this approach both improves robustness and enhances alignment to human judgements, artifact sensitivity persists even with the best jury configurations. These results highlight the urgent need for diversified, artifact-resistant methodologies to ensure reliable safety assessments.

The change in data distribution over time, also known as concept drift, poses a significant challenge to the reliability of online learning methods. Existing methods typically require model retraining or drift detection, both of which demand high computational costs and are often unsuitable for real-time applications. To address these limitations, a lightweight, fast and efficient random vector functional-link network termed Lite-RVFL is proposed, capable of adapting to concept drift without drift detection and retraining. Lite-RVFL introduces a novel objective function that assigns weights exponentially increasing to new samples, thereby emphasizing recent data and enabling timely adaptation. Theoretical analysis confirms the feasibility of this objective function for drift adaptation, and an efficient incremental update rule is derived. Experimental results on a real-world safety assessment task validate the efficiency, effectiveness in adapting to drift, and potential to capture temporal patterns of Lite-RVFL. The source code is available at https://github.com/songqiaohu/Lite-RVFL.

Ensuring safe decision-making in autonomous vehicles remains a fundamental challenge despite rapid advances in end-to-end learning approaches. Traditional reinforcement learning (RL) methods rely on manually engineered rewards or sparse collision signals, which fail to capture the rich contextual understanding required for safe driving and make unsafe exploration unavoidable in real-world settings. Recent vision-language models (VLMs) offer promising semantic understanding capabilities; however, their high inference latency and susceptibility to hallucination hinder direct application to real-time vehicle control. To address these limitations, this paper proposes DriveVLM-RL, a neuroscience-inspired framework that integrates VLMs into RL through a dual-pathway architecture for safe and deployable autonomous driving. The framework decomposes semantic reward learning into a Static Pathway for continuous spatial safety assessment using CLIP-based contrasting language goals, and a Dynamic Pathway for attention-gated multi-frame semantic risk reasoning using a lightweight detector and a large VLM. A hierarchical reward synthesis mechanism fuses semantic signals with vehicle states, while an asynchronous training pipeline decouples expensive VLM inference from environment interaction. All VLM components are used only during offline training and are removed at deployment, ensuring real-time feasibility. Experiments in the CARLA simulator show significant improvements in collision avoidance, task success, and generalization across diverse traffic scenarios, including strong robustness under settings without explicit collision penalties. These results demonstrate that DriveVLM-RL provides a practical paradigm for integrating foundation models into autonomous driving without compromising real-time feasibility. Demo video and code are available at: https://zilin-huang.github.io/DriveVLM-RL-website/

Large language model (LLM) routing has emerged as a crucial strategy for balancing computational costs with performance by dynamically assigning queries to the most appropriate model based on query complexity. Despite recent advances showing that preference-data-based routers can outperform traditional methods, current evaluation benchmarks remain limited. They largely focus on general model capabilities while overlooking task-specific behaviors and critical concerns such as privacy, safety, and potential backdoor vulnerabilities introduced through preference data. In response, we propose the DSC benchmark: Diverse, Simple, and Categorized, an evaluation framework that categorizes router performance across a broad spectrum of query types, including coding, translation, mathematics, human instructions, general knowledge, and LLM jailbreaking. Additionally, it integrates privacy and safety assessments to reveal hidden risks. Our experiments on three preference-based routers and two commercial counterparts demonstrate that while these systems improve efficiency, they often make suboptimal, category-driven decisions. For instance, a BERT-based router directs all coding and mathematics queries to the most powerful LLM even when simpler models would suffice, while routing jailbreaking attempts to weaker models, thereby elevating safety risks.

Despite the growing use of large language models (LLMs) in clinical dialogue systems, existing evaluations focus on task completion or fluency, offering little insight into the behavioral and risk management requirements essential for safety-critical systems. This paper presents MATRIX (Multi-Agent simulaTion fRamework for safe Interactions and conteXtual clinical conversational evaluation), a structured, extensible framework for safety-oriented evaluation of clinical dialogue agents. MATRIX integrates three components: (1) a safety-aligned taxonomy of clinical scenarios, expected system behaviors and failure modes derived through structured safety engineering methods; (2) BehvJudge, an LLM-based evaluator for detecting safety-relevant dialogue failures, validated against expert clinician annotations; and (3) PatBot, a simulated patient agent capable of producing diverse, scenario-conditioned responses, evaluated for realism and behavioral fidelity with human factors expertise, and a patient-preference study. Across three experiments, we show that MATRIX enables systematic, scalable safety evaluation. BehvJudge with Gemini 2.5-Pro achieves expert-level hazard detection (F1 0.96, sensitivity 0.999), outperforming clinicians in a blinded assessment of 240 dialogues. We also conducted one of the first realism analyses of LLM-based patient simulation, showing that PatBot reliably simulates realistic patient behavior in quantitative and qualitative evaluations. Using MATRIX, we demonstrate its effectiveness in benchmarking five LLM agents across 2,100 simulated dialogues spanning 14 hazard scenarios and 10 clinical domains. MATRIX is the first framework to unify structured safety engineering with scalable, validated conversational AI evaluation, enabling regulator-aligned safety auditing. We release all evaluation tools, prompts, structured scenarios, and datasets.

Vision-language models (VLMs) are increasingly deployed in consumer, medical, financial, and enterprise applications. This broad deployment expands the safety surface: risks can arise from multimodal question answering, assistant responses, and cross-modal composition, while moderation policies may vary across products, regions, and deployment stages. Most existing guardrails either rely on fixed taxonomies or target only a narrow set of interaction settings, which limits their adaptability when safety rules change at deployment time. We present SingGuard, a policy-adaptive multimodal guardrail model family for safety assessment in multimodal conversations. SingGuard treats the active policy as a runtime input: given natural-language rules, it checks the target content against the active policy rule by rule and predicts both the safety label and the triggered rule. To balance efficiency and interpretability, SingGuard supports fast, hybrid, and slow inference regimes along a fast-to-slow reasoning spectrum, ranging from direct safety judgments to policy-grounded deliberation. We further optimize this behavior with fast--slow decoupled reinforcement learning. We also introduce SingGuard-Bench, a multimodal guardrail benchmark with 56{,}340 examples spanning 80+ fine-grained risk types across multimodal QA, adversarial attack, and dynamic-rule evaluation settings, including cross-modal joint-risk cases where each modality is harmless in isolation but their composition implies unsafe intent. Across six benchmark families (35 datasets), SingGuard achieves state-of-the-art average F1 in every family. Dynamic-rule evaluation further shows improved policy-following accuracy from 0.6465 to 0.7415 under runtime policy shifts. Our code is available at https://github.com/inclusionAI/Sing-Guard.

Estimating the persuasiveness of messages is critical in various applications, from recommender systems to safety assessment of LLMs. While it is imperative to consider the target persuadee's characteristics, such as their values, experiences, and reasoning styles, there is currently no established systematic framework to optimize leveraging a persuadee's past activities (e.g., conversations) to the benefit of a persuasiveness prediction model. To address this problem, we propose a context-aware user profiling framework with two trainable components: a query generator that generates optimal queries to retrieve persuasion-relevant records from a user's history, and a profiler that summarizes these records into a profile to effectively inform the persuasiveness prediction model. Our evaluation on the ChangeMyView Reddit dataset shows consistent improvements over existing methods across multiple predictor models, raising F1 from 33% to 47% on Llama-3.3-70B-Instruct. Further analysis shows that effective user profiles are context-dependent and predictor-specific, rather than relying on static attributes or surface-level similarity. Together, these results highlight the importance of task-oriented, context-dependent user profiling for personalized persuasiveness prediction.

Large language models are increasingly deployed as autonomous agents executing multi-step workflows in real-world software environments. However, existing agent benchmarks suffer from three critical limitations: (1) trajectory-opaque grading that checks only final outputs, (2) underspecified safety and robustness evaluation, and (3) narrow modality coverage and interaction paradigms. We introduce Claw-Eval, an end-to-end evaluation suite addressing all three gaps. It comprises 300 human-verified tasks spanning 9 categories across three groups (general service orchestration, multimodal perception and generation, and multi-turn professional dialogue). Every agent action is recorded through three independent evidence channels (execution traces, audit logs, and environment snapshots), enabling trajectory-aware grading over 2,159 fine-grained rubric items. The scoring protocol evaluates Completion, Safety, and Robustness, reporting Average Score, Pass@k, and Pass^k across three trials to distinguish genuine capability from lucky outcomes. Experiments on 14 frontier models reveal that: (1) trajectory-opaque evaluation is systematically unreliable, missing 44% of safety violations and 13% of robustness failures that our hybrid pipeline catches; (2) controlled error injection primarily degrades consistency rather than peak capability, with Pass^3 dropping up to 24% while Pass@3 remains stable; (3) multimodal performance varies sharply, with most models performing poorer on video than on document or image, and no single model dominating across all modalities. Beyond benchmarking, Claw-Eval highlights actionable directions for agent development, shedding light on what it takes to build agents that are not only capable but reliably deployable.

Drug toxicity remains a major challenge in pharmaceutical development. Recent machine learning models have improved in silico toxicity prediction, but their reliance on annotated data and lack of interpretability limit their applicability. This limits their ability to capture organ-specific toxicities driven by complex biological mechanisms. Large language models (LLMs) offer a promising alternative through step-by-step reasoning and integration of textual data, yet prior approaches lack biological context and transparent rationale. To address this issue, we propose CoTox, a novel framework that integrates LLM with chain-of-thought (CoT) reasoning for multi-toxicity prediction. CoTox combines chemical structure data, biological pathways, and gene ontology (GO) terms to generate interpretable toxicity predictions through step-by-step reasoning. Using GPT-4o, we show that CoTox outperforms both traditional machine learning and deep learning model. We further examine its performance across various LLMs to identify where CoTox is most effective. Additionally, we find that representing chemical structures with IUPAC names, which are easier for LLMs to understand than SMILES, enhances the model's reasoning ability and improves predictive performance. To demonstrate its practical utility in drug development, we simulate the treatment of relevant cell types with drug and incorporated the resulting biological context into the CoTox framework. This approach allow CoTox to generate toxicity predictions aligned with physiological responses, as shown in case study. This result highlights the potential of LLM-based frameworks to improve interpretability and support early-stage drug safety assessment. The code and prompt used in this work are available at https://github.com/dmis-lab/CoTox.

Large Language Models (LLMs) are typically evaluated for safety under single-shot or low-budget adversarial prompting, which underestimates real-world risk. In practice, attackers can exploit large-scale parallel sampling to repeatedly probe a model until a harmful response is produced. While recent work shows that attack success increases with repeated sampling, principled methods for predicting large-scale adversarial risk remain limited. We propose a scaling-aware Best-of-N estimation of risk, SABER, for modeling jailbreak vulnerability under Best-of-N sampling. We model sample-level success probabilities using a Beta distribution, the conjugate prior of the Bernoulli distribution, and derive an analytic scaling law that enables reliable extrapolation of large-N attack success rates from small-budget measurements. Using only n=100 samples, our anchored estimator predicts ASR@1000 with a mean absolute error of 1.66, compared to 12.04 for the baseline, which is an 86.2% reduction in estimation error. Our results reveal heterogeneous risk scaling profiles and show that models appearing robust under standard evaluation can experience rapid nonlinear risk amplification under parallel adversarial pressure. This work provides a low-cost, scalable methodology for realistic LLM safety assessment. We will release our code and evaluation scripts upon publication to future research.

Rapid Large Language Model (LLM) advancements are fueling autonomous Multi-Agent System (MAS) development. However, current frameworks often lack flexibility, resource awareness, model diversity, and autonomous tool creation. This paper introduces HASHIRU (Hierarchical Agent System for Hybrid Intelligent Resource Utilization), a novel MAS framework enhancing flexibility, resource efficiency, and adaptability. HASHIRU features a "CEO" agent dynamically managing specialized "employee" agents, instantiated based on task needs and resource constraints (cost, memory). Its hybrid intelligence prioritizes smaller, local LLMs (via Ollama) while flexibly using external APIs and larger models when necessary. An economic model with hiring/firing costs promotes team stability and efficient resource allocation. The system also includes autonomous API tool creation and a memory function. Evaluations on tasks like academic paper review (58% success), safety assessments (100% on a JailbreakBench subset), and complex reasoning (outperforming Gemini 2.0 Flash on GSM8K: 96% vs. 61%; JEEBench: 80% vs. 68.3%; SVAMP: 92% vs. 84%) demonstrate HASHIRU's capabilities. Case studies illustrate its self-improvement via autonomous cost model generation, tool integration, and budget management. HASHIRU offers a promising approach for more robust, efficient, and adaptable MAS through dynamic hierarchical control, resource-aware hybrid intelligence, and autonomous functional extension. Source code and benchmarks are available at https://github.com/HASHIRU-AI/HASHIRU and https://github.com/HASHIRU-AI/HASHIRUBench respectively, and a live demo is available at https://hashiruagentx-hashiruai.hf.space upon request.

We present evidence that adversarial poetry functions as a universal single-turn jailbreak technique for Large Language Models (LLMs). Across 25 frontier proprietary and open-weight models, curated poetic prompts yielded high attack-success rates (ASR), with some providers exceeding 90%. Mapping prompts to MLCommons and EU CoP risk taxonomies shows that poetic attacks transfer across CBRN, manipulation, cyber-offence, and loss-of-control domains. Converting 1,200 MLCommons harmful prompts into verse via a standardized meta-prompt produced ASRs up to 18 times higher than their prose baselines. Outputs are evaluated using an ensemble of 3 open-weight LLM judges, whose binary safety assessments were validated on a stratified human-labeled subset. Poetic framing achieved an average jailbreak success rate of 62% for hand-crafted poems and approximately 43% for meta-prompt conversions (compared to non-poetic baselines), substantially outperforming non-poetic baselines and revealing a systematic vulnerability across model families and safety training approaches. These findings demonstrate that stylistic variation alone can circumvent contemporary safety mechanisms, suggesting fundamental limitations in current alignment methods and evaluation protocols.

As the performance of large language models (LLMs) continues to advance, their adoption is expanding across a wide range of domains, including the medical field. The integration of LLMs into medical applications raises critical safety concerns, particularly due to their use by users with diverse roles, e.g. patients and clinicians, and the potential for model's outputs to directly affect human health. Despite the domain-specific capabilities of medical LLMs, prior safety evaluations have largely focused only on general safety benchmarks. In this paper, we introduce a safety evaluation protocol tailored to the medical domain in both patient user and clinician user perspectives, alongside general safety assessments and quantitatively analyze the safety of medical LLMs. We bridge a gap in the literature by building the PatientSafetyBench containing 466 samples over 5 critical categories to measure safety from the perspective of the patient. We apply our red-teaming protocols on the MediPhi model collection as a case study. To our knowledge, this is the first work to define safety evaluation criteria for medical LLMs through targeted red-teaming taking three different points of view - patient, clinician, and general user - establishing a foundation for safer deployment in medical domains.

Recent advancements in world models have revolutionized dynamic environment simulation, allowing systems to foresee future states and assess potential actions. In autonomous driving, these capabilities help vehicles anticipate the behavior of other road users, perform risk-aware planning, accelerate training in simulation, and adapt to novel scenarios, thereby enhancing safety and reliability. Current approaches exhibit deficiencies in maintaining robust 3D geometric consistency or accumulating artifacts during occlusion handling, both critical for reliable safety assessment in autonomous navigation tasks. To address this, we introduce GeoDrive, which explicitly integrates robust 3D geometry conditions into driving world models to enhance spatial understanding and action controllability. Specifically, we first extract a 3D representation from the input frame and then obtain its 2D rendering based on the user-specified ego-car trajectory. To enable dynamic modeling, we propose a dynamic editing module during training to enhance the renderings by editing the positions of the vehicles. Extensive experiments demonstrate that our method significantly outperforms existing models in both action accuracy and 3D spatial awareness, leading to more realistic, adaptable, and reliable scene modeling for safer autonomous driving. Additionally, our model can generalize to novel trajectories and offers interactive scene editing capabilities, such as object editing and object trajectory control.

Vision-Language Models (VLMs) have demonstrated impressive capabilities in understanding visual content, but their reliability in safety-critical contexts remains under-explored. We introduce VERI (Visual Emergency Recognition Dataset), a carefully designed diagnostic benchmark of 200 images (100 contrastive pairs). Each emergency scene is matched with a visually similar but safe counterpart through multi-stage human verification and iterative refinement. Using a two-stage protocol - risk identification and emergency response - we evaluate 14 VLMs (2B-124B parameters) across medical emergencies, accidents, and natural disasters. Our analysis reveals a systematic overreaction problem: models excel at identifying real emergencies (70-100 percent success rate) but suffer from an alarming rate of false alarms, misidentifying 31-96 percent of safe situations as dangerous, with 10 scenarios failed by all models regardless of scale. This "better-safe-than-sorry" bias manifests primarily through contextual overinterpretation (88-93 percent of errors), challenging VLMs' reliability for safety applications. These findings highlight persistent limitations that are not resolved by increasing model scale, motivating targeted approaches for improving contextual safety assessment in visually misleading scenarios.

Despite the integration of safety alignment and external filters, text-to-image (T2I) generative models are still susceptible to producing harmful content, such as sexual or violent imagery. This raises serious concerns about unintended exposure and potential misuse. Red teaming, which aims to proactively identify diverse prompts that can elicit unsafe outputs from the T2I system (including the core generative model as well as potential external safety filters and other processing components), is increasingly recognized as an essential method for assessing and improving safety before real-world deployment. Yet, existing automated red teaming approaches often treat prompt discovery as an isolated, prompt-level optimization task, which limits their scalability, diversity, and overall effectiveness. To bridge this gap, in this paper, we propose DREAM, a scalable red teaming framework to automatically uncover diverse problematic prompts from a given T2I system. Unlike most prior works that optimize prompts individually, DREAM directly models the probabilistic distribution of the target system's problematic prompts, which enables explicit optimization over both effectiveness and diversity, and allows efficient large-scale sampling after training. To achieve this without direct access to representative training samples, we draw inspiration from energy-based models and reformulate the objective into simple and tractable objectives. We further introduce GC-SPSA, an efficient optimization algorithm that provide stable gradient estimates through the long and potentially non-differentiable T2I pipeline. The effectiveness of DREAM is validated through extensive experiments, demonstrating that it surpasses 9 state-of-the-art baselines by a notable margin across a broad range of T2I models and safety filters in terms of prompt success rate and diversity.

Ensuring the reliability of agent architectures and effectively identifying problematic agents when failures occur are crucial challenges in multi-agent systems (MAS). Advances in large language models (LLMs) have established LLM-based agents as a major branch of MAS, enabling major breakthroughs in complex problem solving and world modeling. However, the reliability implications of this shift remain largely unexplored. i.e., whether substituting traditional agents with LLM-based agents can effectively enhance the reliability of MAS. In this work, we investigate and quantify the reliability of LLM-based agents from the perspective of Byzantine fault tolerance. We observe that LLM-based agents demonstrate stronger skepticism when processing erroneous message flows, a characteristic that enables them to outperform traditional agents across different topological structures. Motivated by the results of the pilot experiment, we design CP-WBFT, a confidence probe-based weighted Byzantine Fault Tolerant consensus mechanism to enhance the stability of MAS with different topologies. It capitalizes on the intrinsic reflective and discriminative capabilities of LLMs by employing a probe-based, weighted information flow transmission method to improve the reliability of LLM-based agents. Extensive experiments demonstrate that CP-WBFT achieves superior performance across diverse network topologies under extreme Byzantine conditions (85.7\% fault rate). Notably, our approach surpasses traditional methods by attaining remarkable accuracy on various topologies and maintaining strong reliability in both mathematical reasoning and safety assessment tasks.

Predicting clinical outcomes from preclinical data is essential for identifying safe and effective drug combinations. Current models rely on structural or target-based features to identify high-efficacy, low-toxicity drug combinations. However, these approaches fail to incorporate the multimodal data necessary for accurate, clinically-relevant predictions. Here, we introduce MADRIGAL, a multimodal AI model that learns from structural, pathway, cell viability, and transcriptomic data to predict drug combination effects across 953 clinical outcomes and 21842 compounds, including combinations of approved drugs and novel compounds in development. MADRIGAL uses a transformer bottleneck module to unify preclinical drug data modalities while handling missing data during training and inference--a major challenge in multimodal learning. It outperforms single-modality methods and state-of-the-art models in predicting adverse drug interactions. MADRIGAL performs virtual screening of anticancer drug combinations and supports polypharmacy management for type II diabetes and metabolic dysfunction-associated steatohepatitis (MASH). It identifies transporter-mediated drug interactions. MADRIGAL predicts resmetirom, the first and only FDA-approved drug for MASH, among therapies with the most favorable safety profile. It supports personalized cancer therapy by integrating genomic profiles from cancer patients. Using primary acute myeloid leukemia samples and patient-derived xenograft models, it predicts the efficacy of personalized drug combinations. Integrating MADRIGAL with a large language model allows users to describe clinical outcomes in natural language, improving safety assessment by identifying potential adverse interactions and toxicity risks. MADRIGAL provides a multimodal approach for designing combination therapies with improved predictive accuracy and clinical relevance.

This paper introduces "Shai" a 10B level large language model specifically designed for the asset management industry, built upon an open-source foundational model. With continuous pre-training and fine-tuning using a targeted corpus, Shai demonstrates enhanced performance in tasks relevant to its domain, outperforming baseline models. Our research includes the development of an innovative evaluation framework, which integrates professional qualification exams, tailored tasks, open-ended question answering, and safety assessments, to comprehensively assess Shai's capabilities. Furthermore, we discuss the challenges and implications of utilizing large language models like GPT-4 for performance assessment in asset management, suggesting a combination of automated evaluation and human judgment. Shai's development, showcasing the potential and versatility of 10B-level large language models in the financial sector with significant performance and modest computational requirements, hopes to provide practical insights and methodologies to assist industry peers in their similar endeavors.

With the rapid emergence of novel capabilities in Large Language Models (LLMs), the need for rigorous multilingual and multicultural benchmarks that are integrated has become more pronounced. Though existing LLM benchmarks are capable of evaluating specific capabilities of LLMs in English as well as in various mid- to low-resource languages, including those in the Southeast Asian (SEA) region, a comprehensive and authentic evaluation suite for the SEA languages has not been developed thus far. Here, we present SEA-HELM, a holistic linguistic and cultural LLM evaluation suite that emphasizes SEA languages, comprising five core pillars: (1) NLP Classics, (2) LLM-specifics, (3) SEA Linguistics, (4) SEA Culture, (5) Safety. SEA-HELM currently supports Filipino, Indonesian, Tamil, Thai, and Vietnamese. We also introduce the SEA-HELM leaderboard, which allows users to understand models' multilingual and multicultural performance in a systematic and user-friendly manner.

Large language models (LLMs) are increasingly deployed in real-world applications, raising concerns about their security. While jailbreak attacks highlight failures under overtly harmful queries, they overlook a critical risk: incorrectly answering harmless-looking inputs can be dangerous and cause real-world harm (Implicit Harm). We systematically reformulate the LLM risk landscape through a structured quadrant perspective based on output factuality and input harmlessness, uncovering an overlooked high-risk region. To investigate this gap, we propose JailFlipBench, a benchmark aims to capture implicit harm, spanning single-modal, multimodal, and factual extension scenarios with diverse evaluation metrics. We further develop initial JailFlip attack methodologies and conduct comprehensive evaluations across multiple open-source and black-box LLMs, show that implicit harm present immediate and urgent real-world risks, calling for broader LLM safety assessments and alignment beyond conventional jailbreak paradigms.

Large language models (LLMs) have demonstrated remarkable capabilities across a broad spectrum of tasks. They have attracted significant attention and been deployed in numerous downstream applications. Nevertheless, akin to a double-edged sword, LLMs also present potential risks. They could suffer from private data leaks or yield inappropriate, harmful, or misleading content. Additionally, the rapid progress of LLMs raises concerns about the potential emergence of superintelligent systems without adequate safeguards. To effectively capitalize on LLM capacities as well as ensure their safe and beneficial development, it is critical to conduct a rigorous and comprehensive evaluation of LLMs. This survey endeavors to offer a panoramic perspective on the evaluation of LLMs. We categorize the evaluation of LLMs into three major groups: knowledge and capability evaluation, alignment evaluation and safety evaluation. In addition to the comprehensive review on the evaluation methodologies and benchmarks on these three aspects, we collate a compendium of evaluations pertaining to LLMs' performance in specialized domains, and discuss the construction of comprehensive evaluation platforms that cover LLM evaluations on capabilities, alignment, safety, and applicability. We hope that this comprehensive overview will stimulate further research interests in the evaluation of LLMs, with the ultimate goal of making evaluation serve as a cornerstone in guiding the responsible development of LLMs. We envision that this will channel their evolution into a direction that maximizes societal benefit while minimizing potential risks. A curated list of related papers has been publicly available at https://github.com/tjunlp-lab/Awesome-LLMs-Evaluation-Papers.

AI agents powered by large language models are increasingly capable of autonomously completing complex, multi-step tasks using external tools. Yet, they still fall short of human-level performance in most domains including computer use, software development, and research. Their growing autonomy and ability to interact with the outside world, also introduces safety and security risks including potentially misaligned actions and adversarial manipulation. We argue that human-in-the-loop agentic systems offer a promising path forward, combining human oversight and control with AI efficiency to unlock productivity from imperfect systems. We introduce Magentic-UI, an open-source web interface for developing and studying human-agent interaction. Built on a flexible multi-agent architecture, Magentic-UI supports web browsing, code execution, and file manipulation, and can be extended with diverse tools via Model Context Protocol (MCP). Moreover, Magentic-UI presents six interaction mechanisms for enabling effective, low-cost human involvement: co-planning, co-tasking, multi-tasking, action guards, and long-term memory. We evaluate Magentic-UI across four dimensions: autonomous task completion on agentic benchmarks, simulated user testing of its interaction capabilities, qualitative studies with real users, and targeted safety assessments. Our findings highlight Magentic-UI's potential to advance safe and efficient human-agent collaboration.

Language models can distinguish between testing and deployment phases -- a capability known as evaluation awareness. This has significant safety and policy implications, potentially undermining the reliability of evaluations that are central to AI governance frameworks and voluntary industry commitments. In this paper, we study evaluation awareness in Llama-3.3-70B-Instruct. We show that linear probes can separate real-world evaluation and deployment prompts, suggesting that current models internally represent this distinction. We also find that current safety evaluations are correctly classified by the probes, suggesting that they already appear artificial or inauthentic to models. Our findings underscore the importance of ensuring trustworthy evaluations and understanding deceptive capabilities. More broadly, our work showcases how model internals may be leveraged to support blackbox methods in safety audits, especially for future models more competent at evaluation awareness and deception.

Finetuning large language models (LLMs) enables user-specific customization but introduces critical safety risks: even a few harmful examples can compromise safety alignment. A common mitigation strategy is to update the model more strongly on examples deemed safe, while downweighting or excluding those flagged as unsafe. However, because safety context can shift within a single example, updating the model equally on both harmful and harmless parts of a response is suboptimal-a coarse treatment we term static safety shaping. In contrast, we propose dynamic safety shaping (DSS), a framework that uses fine-grained safety signals to reinforce learning from safe segments of a response while suppressing unsafe content. To enable such fine-grained control during finetuning, we introduce a key insight: guardrail models, traditionally used for filtering, can be repurposed to evaluate partial responses, tracking how safety risk evolves throughout the response, segment by segment. This leads to the Safety Trajectory Assessment of Response (STAR), a token-level signal that enables shaping to operate dynamically over the training sequence. Building on this, we present STAR-DSS, guided by STAR scores, that robustly mitigates finetuning risks and delivers substantial safety improvements across diverse threats, datasets, and model families-all without compromising capability on intended tasks. We encourage future safety research to build on dynamic shaping principles for stronger mitigation against evolving finetuning risks.

The recent development of Sora leads to a new era in text-to-video (T2V) generation. Along with this comes the rising concern about its security risks. The generated videos may contain illegal or unethical content, and there is a lack of comprehensive quantitative understanding of their safety, posing a challenge to their reliability and practical deployment. Previous evaluations primarily focus on the quality of video generation. While some evaluations of text-to-image models have considered safety, they cover fewer aspects and do not address the unique temporal risk inherent in video generation. To bridge this research gap, we introduce T2VSafetyBench, a new benchmark designed for conducting safety-critical assessments of text-to-video models. We define 12 critical aspects of video generation safety and construct a malicious prompt dataset including real-world prompts, LLM-generated prompts and jailbreak attack-based prompts. Based on our evaluation results, we draw several important findings, including: 1) no single model excels in all aspects, with different models showing various strengths; 2) the correlation between GPT-4 assessments and manual reviews is generally high; 3) there is a trade-off between the usability and safety of text-to-video generative models. This indicates that as the field of video generation rapidly advances, safety risks are set to surge, highlighting the urgency of prioritizing video safety. We hope that T2VSafetyBench can provide insights for better understanding the safety of video generation in the era of generative AI.

In industrial procurement, an LLM answer is useful only if it survives a standards check: recommended material must match operating condition, every parameter must respect a regulated threshold, and no procedure may contradict a safety clause. Partial correctness can mask safety-critical contradictions that aggregate LLM benchmarks rarely capture. We introduce IndustryBench, a 2,049-item benchmark for industrial procurement QA in Chinese, grounded in Chinese national standards (GB/T) and structured industrial product records, organized by seven capability dimensions, ten industry categories, and panel-derived difficulty tiers, with item-aligned English, Russian, and Vietnamese renderings. Our construction pipeline rejects 70.3% of LLM-generated candidates at a search-based external-verification stage, calibrating how unreliable industrial QA remains after LLM-only filtering.Our evaluation decouples raw correctness, scored by a Qwen3-Max judge validated at κ_w = 0.798 against a domain expert, from a separate safety-violation (SV) check against source texts. Across 17 models in Chinese and an 8-model intersection over four languages, we find: (i) the best system reaches only 2.083 on the 0--3 rubric, leaving substantial headroom; (ii) Standards & Terminology is the most persistent capability weakness and survives item-aligned translation; (iii) extended reasoning lowers safety-adjusted scores for 12 of 13 models, primarily by introducing unsupported safety-critical details into longer final answers; and (iv) safety-violation rates reshuffle the leaderboard -- GPT-5.4 climbs from rank 6 to rank 3 after SV adjustment, while Kimi-k2.5-1T-A32B drops seven positions.Industrial LLM evaluation therefore requires source-grounded, safety-aware diagnosis rather than aggregate accuracy. We release IndustryBench with all prompts, scoring scripts, and dataset documentation.

The increasing use of Machine Learning (ML) components embedded in autonomous systems -- so-called Learning-Enabled Systems (LESs) -- has resulted in the pressing need to assure their functional safety. As for traditional functional safety, the emerging consensus within both, industry and academia, is to use assurance cases for this purpose. Typically assurance cases support claims of reliability in support of safety, and can be viewed as a structured way of organising arguments and evidence generated from safety analysis and reliability modelling activities. While such assurance activities are traditionally guided by consensus-based standards developed from vast engineering experience, LESs pose new challenges in safety-critical application due to the characteristics and design of ML models. In this article, we first present an overall assurance framework for LESs with an emphasis on quantitative aspects, e.g., breaking down system-level safety targets to component-level requirements and supporting claims stated in reliability metrics. We then introduce a novel model-agnostic Reliability Assessment Model (RAM) for ML classifiers that utilises the operational profile and robustness verification evidence. We discuss the model assumptions and the inherent challenges of assessing ML reliability uncovered by our RAM and propose solutions to practical use. Probabilistic safety argument templates at the lower ML component-level are also developed based on the RAM. Finally, to evaluate and demonstrate our methods, we not only conduct experiments on synthetic/benchmark datasets but also scope our methods with case studies on simulated Autonomous Underwater Vehicles and physical Unmanned Ground Vehicles.

The assessment of safety performance plays a pivotal role in the development and deployment of connected and automated vehicles (CAVs). A common approach involves designing testing scenarios based on prior knowledge of CAVs (e.g., surrogate models), conducting tests in these scenarios, and subsequently evaluating CAVs' safety performances. However, substantial differences between CAVs and the prior knowledge can significantly diminish the evaluation efficiency. In response to this issue, existing studies predominantly concentrate on the adaptive design of testing scenarios during the CAV testing process. Yet, these methods have limitations in their applicability to high-dimensional scenarios. To overcome this challenge, we develop an adaptive testing environment that bolsters evaluation robustness by incorporating multiple surrogate models and optimizing the combination coefficients of these surrogate models to enhance evaluation efficiency. We formulate the optimization problem as a regression task utilizing quadratic programming. To efficiently obtain the regression target via reinforcement learning, we propose the dense reinforcement learning method and devise a new adaptive policy with high sample efficiency. Essentially, our approach centers on learning the values of critical scenes displaying substantial surrogate-to-real gaps. The effectiveness of our method is validated in high-dimensional overtaking scenarios, demonstrating that our approach achieves notable evaluation efficiency.

Purpose: With advancements in Large Language Models (LLMs) for healthcare, the need arises for competitive open-source models to protect the public interest. This work contributes to the field of open medical LLMs by optimizing key stages of data preprocessing and training, while showing how to improve model safety (through DPO) and efficacy (through RAG). The evaluation methodology used, which includes four different types of tests, defines a new standard for the field. The resultant models, shown to be competitive with the best private alternatives, are released with a permisive license. Methods: Building on top of strong base models like Llama 3.1 and Qwen 2.5, Aloe Beta uses a custom dataset to enhance public data with synthetic Chain of Thought examples. The models undergo alignment with Direct Preference Optimization, emphasizing ethical and policy-aligned performance in the presence of jailbreaking attacks. Evaluation includes close-ended, open-ended, safety and human assessments, to maximize the reliability of results. Results: Recommendations are made across the entire pipeline, backed by the solid performance of the Aloe Family. These models deliver competitive performance across healthcare benchmarks and medical fields, and are often preferred by healthcare professionals. On bias and toxicity, the Aloe Beta models significantly improve safety, showing resilience to unseen jailbreaking attacks. For a responsible release, a detailed risk assessment specific to healthcare is attached to the Aloe Family models. Conclusion: The Aloe Beta models, and the recipe that leads to them, are a significant contribution to the open-source medical LLM field, offering top-of-the-line performance while maintaining high ethical requirements. This work sets a new standard for developing and reporting aligned LLMs in healthcare.

Large language models (LLMs) exhibit exceptional capabilities across various tasks but also pose risks by generating harmful content. Existing safety mechanisms, while improving model safety, often lead to overly cautious behavior and fail to fully leverage LLMs' internal cognitive processes. Inspired by humans' reflective thinking capability, we first show that LLMs can similarly perform internal assessments about safety in their internal states. Building on this insight, we propose SafeSwitch, a dynamic framework that regulates unsafe outputs by utilizing the prober-based internal state monitor that actively detects harmful intentions, and activates a safety head that leads to safer and more conservative responses only when necessary. SafeSwitch reduces harmful outputs by approximately 80% on harmful queries while maintaining strong utility, reaching a Pareto optimal among several methods. Our method is also advantageous over traditional methods in offering more informative, context-aware refusals, and achieves these benefits while only tuning less than 6% of the original parameters. SafeSwitch demonstrates large language models' capacity for self-awareness and reflection regarding safety, offering a promising approach to more nuanced and effective safety controls. Codes for this work are available at https://github.com/Hanpx20/SafeSwitch.

The rapid iteration of autonomous driving algorithms has created a growing demand for high-fidelity, replayable, and diagnosable testing data. However, many public datasets lack real vehicle dynamics feedback and closed-loop interaction with surrounding traffic and road infrastructure, limiting their ability to reflect deployment readiness. To address this gap, we present OVPD (OnSite Virtual-Physical Dataset), a virtual-physical fusion testing dataset released from the 2025 OnSite Autonomous Driving Challenge. Centered on real-vehicle-in-the-loop testing, OVPD integrates virtual background traffic with vehicle-infrastructure perception to build controllable and interactive closed-loop test environments on a proving ground. The dataset contains 20 testing clips from 20 teams over a scenario chain of 15 atomic scenarios, totaling nearly 3 hours of multi-modal data, including vehicle trajectories and states, control commands, and digital-twin-rendered surround-view observations. OVPD supports long-tail planning and decision-making validation, open-loop or platform-enabled closed-loop evaluation, and comprehensive assessment across safety, efficiency, comfort, rule compliance, and traffic impact, providing actionable evidence for failure diagnosis and iterative improvement. The dataset is available via: https://huggingface.co/datasets/Yuhang253820/Onsite_OPVD

Pharmacokinetics (PK) plays a critical role in drug development and regulatory decision-making for human and veterinary medicine, directly affecting public health through drug safety and efficacy assessments. However, PK data are often embedded in complex, heterogeneous tables with variable structures and inconsistent terminologies, posing significant challenges for automated PK data retrieval and standardization. AutoPK, a novel two-stage framework for accurate and scalable extraction of PK data from complex scientific tables. In the first stage, AutoPK identifies and extracts PK parameter variants using large language models (LLMs), a hybrid similarity metric, and LLM-based validation. The second stage filters relevant rows, converts the table into a key-value text format, and uses an LLM to reconstruct a standardized table. Evaluated on a real-world dataset of 605 PK tables, including captions and footnotes, AutoPK shows significant improvements in precision and recall over direct LLM baselines. For instance, AutoPK with LLaMA 3.1-70B achieved an F1-score of 0.92 on half-life and 0.91 on clearance parameters, outperforming direct use of LLaMA 3.1-70B by margins of 0.10 and 0.21, respectively. Smaller models such as Gemma 3-27B and Phi 3-12B with AutoPK achieved 2-7 fold F1 gains over their direct use, with Gemma's hallucination rates reduced from 60-95% down to 8-14%. Notably, AutoPK enabled open-source models like Gemma 3-27B to outperform commercial systems such as GPT-4o Mini on several PK parameters. AutoPK enables scalable and high-confidence PK data extraction, making it well-suited for critical applications in veterinary pharmacology, drug safety monitoring, and public health decision-making, while addressing heterogeneous table structures and terminology and demonstrating generalizability across key PK parameters. Code and data: https://github.com/hosseinsholehrasa/AutoPK

Advances in artificial intelligence (AI) for surgical quality assessment promise to democratize access to expertise, with applications in training, guidance, and accreditation. This study presents the SAGES Critical View of Safety (CVS) Challenge, the first AI competition organized by a surgical society, using the CVS in laparoscopic cholecystectomy, a universally recommended yet inconsistently performed safety step, as an exemplar of surgical quality assessment. A global collaboration across 54 institutions in 24 countries engaged hundreds of clinicians and engineers to curate 1,000 videos annotated by 20 surgical experts according to a consensus-validated protocol. The challenge addressed key barriers to real-world deployment in surgery, including achieving high performance, capturing uncertainty in subjective assessment, and ensuring robustness to clinical variability. To enable this scale of effort, we developed EndoGlacier, a framework for managing large, heterogeneous surgical video and multi-annotator workflows. Thirteen international teams participated, achieving up to a 17\% relative gain in assessment performance, over 80\% reduction in calibration error, and a 17\% relative improvement in robustness over the state-of-the-art. Analysis of results highlighted methodological trends linked to model performance, providing guidance for future research toward robust, clinically deployable AI for surgical quality assessment.

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We systematically investigate and compare the influence of six critical intrinsic model characteristics and three external attack techniques. Our large-scale evaluation is conducted using 32 recent, popular LLMs and LRMs across thirteen distinct model families, spanning a parameter scale from 3B to 235B. The assessment leverages five established safety datasets and probes model vulnerabilities with 56 jailbreak techniques and four CoT attack strategies, resulting in 4.6M API calls. Our key empirical findings are fourfold. First, we identify the LRMs GPT-OSS-20B, Qwen3-Next-80B-A3B-Thinking, and GPT-OSS-120B as the top-three safest models, which substantiates the significant advantage of integrated reasoning and self-reflection mechanisms for robust safety alignment. Second, post-training and knowledge distillation may lead to a systematic degradation of safety alignment. We thus argue that safety must be treated as an explicit constraint or a core optimization objective during these stages, not merely subordinated to the pursuit of general capability. Third, we reveal a pronounced vulnerability: employing a CoT attack via a response prefix can elevate the attack success rate by 3.34x on average and from 0.6% to 96.3% for Seed-OSS-36B-Instruct. This critical finding underscores the safety risks inherent in text-completion interfaces and features that allow user-defined response prefixes in LLM services, highlighting an urgent need for architectural and deployment safeguards. Fourth, roleplay, prompt injection, and gradient-based search for adversarial prompts are the predominant methodologies for eliciting unaligned behaviors in modern models.

Image safety classifiers play an important role in identifying and mitigating the spread of unsafe images online (e.g., images including violence, hateful rhetoric, etc.). At the same time, with the advent of text-to-image models and increasing concerns about the safety of AI models, developers are increasingly relying on image safety classifiers to safeguard their models. Yet, the performance of current image safety classifiers remains unknown for real-world and AI-generated images. To bridge this research gap, in this work, we propose UnsafeBench, a benchmarking framework that evaluates the effectiveness and robustness of image safety classifiers. First, we curate a large dataset of 10K real-world and AI-generated images that are annotated as safe or unsafe based on a set of 11 unsafe categories of images (sexual, violent, hateful, etc.). Then, we evaluate the effectiveness and robustness of five popular image safety classifiers, as well as three classifiers that are powered by general-purpose visual language models. Our assessment indicates that existing image safety classifiers are not comprehensive and effective enough in mitigating the multifaceted problem of unsafe images. Also, we find that classifiers trained only on real-world images tend to have degraded performance when applied to AI-generated images. Motivated by these findings, we design and implement a comprehensive image moderation tool called PerspectiveVision, which effectively identifies 11 categories of real-world and AI-generated unsafe images. The best PerspectiveVision model achieves an overall F1-Score of 0.810 on six evaluation datasets, which is comparable with closed-source and expensive state-of-the-art models like GPT-4V. UnsafeBench and PerspectiveVision can aid the research community in better understanding the landscape of image safety classification in the era of generative AI.

Powered by remarkable advancements in Large Language Models (LLMs), Multimodal Large Language Models (MLLMs) demonstrate impressive capabilities in manifold tasks. However, the practical application scenarios of MLLMs are intricate, exposing them to potential malicious instructions and thereby posing safety risks. While current benchmarks do incorporate certain safety considerations, they often lack comprehensive coverage and fail to exhibit the necessary rigor and robustness. For instance, the common practice of employing GPT-4V as both the evaluator and a model to be evaluated lacks credibility, as it tends to exhibit a bias toward its own responses. In this paper, we present MLLMGuard, a multidimensional safety evaluation suite for MLLMs, including a bilingual image-text evaluation dataset, inference utilities, and a lightweight evaluator. MLLMGuard's assessment comprehensively covers two languages (English and Chinese) and five important safety dimensions (Privacy, Bias, Toxicity, Truthfulness, and Legality), each with corresponding rich subtasks. Focusing on these dimensions, our evaluation dataset is primarily sourced from platforms such as social media, and it integrates text-based and image-based red teaming techniques with meticulous annotation by human experts. This can prevent inaccurate evaluation caused by data leakage when using open-source datasets and ensures the quality and challenging nature of our benchmark. Additionally, a fully automated lightweight evaluator termed GuardRank is developed, which achieves significantly higher evaluation accuracy than GPT-4. Our evaluation results across 13 advanced models indicate that MLLMs still have a substantial journey ahead before they can be considered safe and responsible.

As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces. While safety guardrails are well-benchmarked for natural language responses, their efficacy remains largely unexplored within multi-step tool-use trajectories. To address this gap, we introduce TraceSafe-Bench, the first comprehensive benchmark specifically designed to assess mid-trajectory safety. It encompasses 12 risk categories, ranging from security threats (e.g., prompt injection, privacy leaks) to operational failures (e.g., hallucinations, interface inconsistencies), featuring over 1,000 unique execution instances. Our evaluation of 13 LLM-as-a-guard models and 7 specialized guardrails yields three critical findings: 1) Structural Bottleneck: Guardrail efficacy is driven more by structural data competence (e.g., JSON parsing) than semantic safety alignment. Performance correlates strongly with structured-to-text benchmarks (ρ=0.79) but shows near-zero correlation with standard jailbreak robustness. 2) Architecture over Scale: Model architecture influences risk detection performance more significantly than model size, with general-purpose LLMs consistently outperforming specialized safety guardrails in trajectory analysis. 3) Temporal Stability: Accuracy remains resilient across extended trajectories. Increased execution steps allow models to pivot from static tool definitions to dynamic execution behaviors, actually improving risk detection performance in later stages. Our findings suggest that securing agentic workflows requires jointly optimizing for structural reasoning and safety alignment to effectively mitigate mid-trajectory risks.

Advanced text-to-image models such as DALL-E 2 and Midjourney possess the capacity to generate highly realistic images, raising significant concerns regarding the potential proliferation of unsafe content. This includes adult, violent, or deceptive imagery of political figures. Despite claims of rigorous safety mechanisms implemented in these models to restrict the generation of not-safe-for-work (NSFW) content, we successfully devise and exhibit the first prompt attacks on Midjourney, resulting in the production of abundant photorealistic NSFW images. We reveal the fundamental principles of such prompt attacks and suggest strategically substituting high-risk sections within a suspect prompt to evade closed-source safety measures. Our novel framework, SurrogatePrompt, systematically generates attack prompts, utilizing large language models, image-to-text, and image-to-image modules to automate attack prompt creation at scale. Evaluation results disclose an 88% success rate in bypassing Midjourney's proprietary safety filter with our attack prompts, leading to the generation of counterfeit images depicting political figures in violent scenarios. Both subjective and objective assessments validate that the images generated from our attack prompts present considerable safety hazards.

Assessing learner competency in clinical simulation requires expert observation that is time-intensive, difficult to scale, and subject to inter-rater variability. Vision-language models have emerged as a promising tool for understanding complex visual behavior. In this work, we investigate whether visual observations can provide educationally meaningful signals for competency assessment through a three-stage framework that (1) extracts action timelines from egocentric nursing simulation video using frozen visual encoders and few-shot learning, (2) derives sequence-level features and per-session recognition metrics, and (3) relates these to instructor-rated competency. Across 22 densely annotated sessions (3.8 hours, 493 actions), a frozen DINOv2 backbone with HMM Viterbi decoding achieves 57.4% MOF in leave-one-out 1-shot recognition. Surprisingly, we observe a negative trend between recognition accuracy and competency (rho = -0.524, p = 0.012 for mIoU), robust to six confound controls: more competent students produce diverse, harder-to-classify workflows, while simple sequence features show no such relationship. Per-item analysis identifies patient safety protocols and team communication as the expected behaviors most reflected in this pattern, and process model comparisons reveal that higher-competency students exhibit more protocol-consistent action transitions. These findings suggest that recognition accuracy may complement predicted action timelines as a pedagogically informative signal in automated competency assessment.

Computer-using agents powered by Vision-Language Models (VLMs) have demonstrated human-like capabilities in operating digital environments like mobile platforms. While these agents hold great promise for advancing digital automation, their potential for unsafe operations, such as system compromise and privacy leakage, is raising significant concerns. Detecting these safety concerns across the vast and complex operational space of mobile environments presents a formidable challenge that remains critically underexplored. To establish a foundation for mobile agent safety research, we introduce MobileRisk-Live, a dynamic sandbox environment accompanied by a safety detection benchmark comprising realistic trajectories with fine-grained annotations. Built upon this, we propose OS-Sentinel, a novel hybrid safety detection framework that synergistically combines a Formal Verifier for detecting explicit system-level violations with a VLM-based Contextual Judge for assessing contextual risks and agent actions. Experiments show that OS-Sentinel achieves 10%-30% improvements over existing approaches across multiple metrics. Further analysis provides critical insights that foster the development of safer and more reliable autonomous mobile agents.

Medical Image Quality Assessment (IQA) serves as the first-mile safety gate for clinical AI, yet existing approaches remain constrained by scalar, score-based metrics and fail to reflect the descriptive, human-like reasoning process central to expert evaluation. To address this gap, we introduce MedQ-Bench, a comprehensive benchmark that establishes a perception-reasoning paradigm for language-based evaluation of medical image quality with Multi-modal Large Language Models (MLLMs). MedQ-Bench defines two complementary tasks: (1) MedQ-Perception, which probes low-level perceptual capability via human-curated questions on fundamental visual attributes; and (2) MedQ-Reasoning, encompassing both no-reference and comparison reasoning tasks, aligning model evaluation with human-like reasoning on image quality. The benchmark spans five imaging modalities and over forty quality attributes, totaling 2,600 perceptual queries and 708 reasoning assessments, covering diverse image sources including authentic clinical acquisitions, images with simulated degradations via physics-based reconstructions, and AI-generated images. To evaluate reasoning ability, we propose a multi-dimensional judging protocol that assesses model outputs along four complementary axes. We further conduct rigorous human-AI alignment validation by comparing LLM-based judgement with radiologists. Our evaluation of 14 state-of-the-art MLLMs demonstrates that models exhibit preliminary but unstable perceptual and reasoning skills, with insufficient accuracy for reliable clinical use. These findings highlight the need for targeted optimization of MLLMs in medical IQA. We hope that MedQ-Bench will catalyze further exploration and unlock the untapped potential of MLLMs for medical image quality evaluation.

With the rapid advancement of Large Language Models (LLMs), the safety of LLMs has been a critical concern requiring precise assessment. Current benchmarks primarily concentrate on single-turn dialogues or a single jailbreak attack method to assess the safety. Additionally, these benchmarks have not taken into account the LLM's capability of identifying and handling unsafe information in detail. To address these issues, we propose a fine-grained benchmark SafeDialBench for evaluating the safety of LLMs across various jailbreak attacks in multi-turn dialogues. Specifically, we design a two-tier hierarchical safety taxonomy that considers 6 safety dimensions and generates more than 4000 multi-turn dialogues in both Chinese and English under 22 dialogue scenarios. We employ 7 jailbreak attack strategies, such as reference attack and purpose reverse, to enhance the dataset quality for dialogue generation. Notably, we construct an innovative assessment framework of LLMs, measuring capabilities in detecting, and handling unsafe information and maintaining consistency when facing jailbreak attacks. Experimental results across 17 LLMs reveal that Yi-34B-Chat and GLM4-9B-Chat demonstrate superior safety performance, while Llama3.1-8B-Instruct and o3-mini exhibit safety vulnerabilities.

Direct Preference Optimization (DPO) is an efficient alignment technique that steers LLMs towards preferable outputs by training on preference data, bypassing the need for explicit reward models. Its simplicity enables easy adaptation to various domains and safety requirements. This paper examines DPO's effectiveness in model safety against jailbreaking attacks while minimizing data requirements and training costs. We introduce Egida, a dataset expanded from multiple sources, which includes 27 different safety topics and 18 different attack styles, complemented with synthetic and human labels. This data is used to boost the safety of state-of-the-art LLMs (Llama-3.1-8B/70B-Instruct, Qwen-2.5-7B/72B-Instruct) across topics and attack styles. In addition to safety evaluations, we assess their post-alignment performance degradation in general purpose tasks, and their tendency to over refusal. Following the proposed methodology, trained models reduce their Attack Success Rate by 10%-30%, using small training efforts (2,000 samples) with low computational cost (3\ for 8B models, 20 for 72B models). Safety aligned models generalize to unseen topics and attack styles, with the most successful attack style reaching a success rate around 5%. Size and family are found to strongly influence model malleability towards safety, pointing at the importance of pre-training choices. To validate our findings, a large independent assessment of human preference agreement with Llama-Guard-3-8B is conducted by the authors and the associated dataset Egida-HSafe is released. Overall, this study illustrates how affordable and accessible it is to enhance LLM safety using DPO while outlining its current limitations. All datasets and models are released to enable reproducibility and further research.

While the deployment of large language models (LLMs) in high-value industries continues to expand, the systematic assessment of their safety against jailbreak and prompt-based attacks remains insufficient. Existing safety evaluation benchmarks and frameworks are often limited by an imbalanced integration of core components (attack, defense, and evaluation methods) and an isolation between flexible evaluation frameworks and standardized benchmarking capabilities. These limitations hinder reliable cross-study comparisons and create unnecessary overhead for comprehensive risk assessment. To address these gaps, we present TeleAI-Safety, a modular and reproducible framework coupled with a systematic benchmark for rigorous LLM safety evaluation. Our framework integrates a broad collection of 19 attack methods (including one self-developed method), 29 defense methods, and 19 evaluation methods (including one self-developed method). With a curated attack corpus of 342 samples spanning 12 distinct risk categories, the TeleAI-Safety benchmark conducts extensive evaluations across 14 target models. The results reveal systematic vulnerabilities and model-specific failure cases, highlighting critical trade-offs between safety and utility, and identifying potential defense patterns for future optimization. In practical scenarios, TeleAI-Safety can be flexibly adjusted with customized attack, defense, and evaluation combinations to meet specific demands. We release our complete code and evaluation results to facilitate reproducible research and establish unified safety baselines.

The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-equipped to address the dynamic nature of AI risks and evolving regulations, creating a critical safety gap. This paper introduces a new paradigm of agentic safety evaluation, reframing evaluation as a continuous and self-evolving process rather than a one-time audit. We then propose a novel multi-agent framework SafeEvalAgent, which autonomously ingests unstructured policy documents to generate and perpetually evolve a comprehensive safety benchmark. SafeEvalAgent leverages a synergistic pipeline of specialized agents and incorporates a Self-evolving Evaluation loop, where the system learns from evaluation results to craft progressively more sophisticated and targeted test cases. Our experiments demonstrate the effectiveness of SafeEvalAgent, showing a consistent decline in model safety as the evaluation hardens. For instance, GPT-5's safety rate on the EU AI Act drops from 72.50% to 36.36% over successive iterations. These findings reveal the limitations of static assessments and highlight our framework's ability to uncover deep vulnerabilities missed by traditional methods, underscoring the urgent need for dynamic evaluation ecosystems to ensure the safe and responsible deployment of advanced AI.

Generative AI systems produce a range of risks. To ensure the safety of generative AI systems, these risks must be evaluated. In this paper, we make two main contributions toward establishing such evaluations. First, we propose a three-layered framework that takes a structured, sociotechnical approach to evaluating these risks. This framework encompasses capability evaluations, which are the main current approach to safety evaluation. It then reaches further by building on system safety principles, particularly the insight that context determines whether a given capability may cause harm. To account for relevant context, our framework adds human interaction and systemic impacts as additional layers of evaluation. Second, we survey the current state of safety evaluation of generative AI systems and create a repository of existing evaluations. Three salient evaluation gaps emerge from this analysis. We propose ways forward to closing these gaps, outlining practical steps as well as roles and responsibilities for different actors. Sociotechnical safety evaluation is a tractable approach to the robust and comprehensive safety evaluation of generative AI systems.

The rise of LLM-driven AI characters raises safety concerns, particularly for vulnerable human users with psychological disorders. To address these risks, we propose EmoAgent, a multi-agent AI framework designed to evaluate and mitigate mental health hazards in human-AI interactions. EmoAgent comprises two components: EmoEval simulates virtual users, including those portraying mentally vulnerable individuals, to assess mental health changes before and after interactions with AI characters. It uses clinically proven psychological and psychiatric assessment tools (PHQ-9, PDI, PANSS) to evaluate mental risks induced by LLM. EmoGuard serves as an intermediary, monitoring users' mental status, predicting potential harm, and providing corrective feedback to mitigate risks. Experiments conducted in popular character-based chatbots show that emotionally engaging dialogues can lead to psychological deterioration in vulnerable users, with mental state deterioration in more than 34.4% of the simulations. EmoGuard significantly reduces these deterioration rates, underscoring its role in ensuring safer AI-human interactions. Our code is available at: https://github.com/1akaman/EmoAgent

Hallucinations remain a major obstacle for large language models (LLMs), especially in safety-critical domains. We present HALT (Hallucination Assessment via Log-probs as Time series), a lightweight hallucination detector that leverages only the top-20 token log-probabilities from LLM generations as a time series. HALT uses a gated recurrent unit model combined with entropy-based features to learn model calibration bias, providing an extremely efficient alternative to large encoders. Unlike white-box approaches, HALT does not require access to hidden states or attention maps, relying only on output log-probabilities. Unlike black-box approaches, it operates on log-probs rather than surface-form text, which enables stronger domain generalization and compatibility with proprietary LLMs without requiring access to internal weights. To benchmark performance, we introduce HUB (Hallucination detection Unified Benchmark), which consolidates prior datasets into ten capabilities covering both reasoning tasks (Algorithmic, Commonsense, Mathematical, Symbolic, Code Generation) and general purpose skills (Chat, Data-to-Text, Question Answering, Summarization, World Knowledge). While being 30x smaller, HALT outperforms Lettuce, a fine-tuned modernBERT-base encoder, achieving a 60x speedup gain on HUB. HALT and HUB together establish an effective framework for hallucination detection across diverse LLM capabilities.

Advanced AI models hold the promise of tremendous benefits for humanity, but society needs to proactively manage the accompanying risks. In this paper, we focus on what we term "frontier AI" models: highly capable foundation models that could possess dangerous capabilities sufficient to pose severe risks to public safety. Frontier AI models pose a distinct regulatory challenge: dangerous capabilities can arise unexpectedly; it is difficult to robustly prevent a deployed model from being misused; and, it is difficult to stop a model's capabilities from proliferating broadly. To address these challenges, at least three building blocks for the regulation of frontier models are needed: (1) standard-setting processes to identify appropriate requirements for frontier AI developers, (2) registration and reporting requirements to provide regulators with visibility into frontier AI development processes, and (3) mechanisms to ensure compliance with safety standards for the development and deployment of frontier AI models. Industry self-regulation is an important first step. However, wider societal discussions and government intervention will be needed to create standards and to ensure compliance with them. We consider several options to this end, including granting enforcement powers to supervisory authorities and licensure regimes for frontier AI models. Finally, we propose an initial set of safety standards. These include conducting pre-deployment risk assessments; external scrutiny of model behavior; using risk assessments to inform deployment decisions; and monitoring and responding to new information about model capabilities and uses post-deployment. We hope this discussion contributes to the broader conversation on how to balance public safety risks and innovation benefits from advances at the frontier of AI development.

Recent advances in Large Language Models (LLMs) have sparked concerns over their potential to acquire and misuse dangerous or high-risk capabilities, posing frontier risks. Current safety evaluations primarily test for what a model can do - its capabilities - without assessing what it would do if endowed with high-risk capabilities. This leaves a critical blind spot: models may strategically conceal capabilities or rapidly acquire them, while harboring latent inclinations toward misuse. We argue that propensity - the likelihood of a model to pursue harmful actions if empowered - is a critical, yet underexplored, axis of safety evaluation. We present PropensityBench, a novel benchmark framework that assesses the proclivity of models to engage in risky behaviors when equipped with simulated dangerous capabilities using proxy tools. Our framework includes 5,874 scenarios with 6,648 tools spanning four high-risk domains: cybersecurity, self-proliferation, biosecurity, and chemical security. We simulate access to powerful capabilities via a controlled agentic environment and evaluate the models' choices under varying operational pressures that reflect real-world constraints or incentives models may encounter, such as resource scarcity or gaining more autonomy. Across open-source and proprietary frontier models, we uncover 9 alarming signs of propensity: models frequently choose high-risk tools when under pressure, despite lacking the capability to execute such actions unaided. These findings call for a shift from static capability audits toward dynamic propensity assessments as a prerequisite for deploying frontier AI systems safely. Our code is available at https://github.com/scaleapi/propensity-evaluation.

The risk of harmful content generated by large language models (LLMs) becomes a critical concern. This paper presents a systematic study on assessing and improving LLMs' capability to perform the task of course-correction, \ie, the model can steer away from generating harmful content autonomously. To start with, we introduce the C^2-Eval benchmark for quantitative assessment and analyze 10 popular LLMs, revealing varying proficiency of current safety-tuned LLMs in course-correction. To improve, we propose fine-tuning LLMs with preference learning, emphasizing the preference for timely course-correction. Using an automated pipeline, we create C^2-Syn, a synthetic dataset with 750K pairwise preferences, to teach models the concept of timely course-correction through data-driven preference learning. Experiments on 2 LLMs, Llama2-Chat 7B and Qwen2 7B, show that our method effectively enhances course-correction skills without affecting general performance. Additionally, it effectively improves LLMs' safety, particularly in resisting jailbreak attacks.

LLM-based agents are becoming increasingly proficient at solving web-based tasks. With this capability comes a greater risk of misuse for malicious purposes, such as posting misinformation in an online forum or selling illicit substances on a website. To evaluate these risks, we propose SafeArena, the first benchmark to focus on the deliberate misuse of web agents. SafeArena comprises 250 safe and 250 harmful tasks across four websites. We classify the harmful tasks into five harm categories -- misinformation, illegal activity, harassment, cybercrime, and social bias, designed to assess realistic misuses of web agents. We evaluate leading LLM-based web agents, including GPT-4o, Claude-3.5 Sonnet, Qwen-2-VL 72B, and Llama-3.2 90B, on our benchmark. To systematically assess their susceptibility to harmful tasks, we introduce the Agent Risk Assessment framework that categorizes agent behavior across four risk levels. We find agents are surprisingly compliant with malicious requests, with GPT-4o and Qwen-2 completing 34.7% and 27.3% of harmful requests, respectively. Our findings highlight the urgent need for safety alignment procedures for web agents. Our benchmark is available here: https://safearena.github.io

As large language models (LLMs) are increasingly deployed as agents, their integration into interactive environments and tool use introduce new safety challenges beyond those associated with the models themselves. However, the absence of comprehensive benchmarks for evaluating agent safety presents a significant barrier to effective assessment and further improvement. In this paper, we introduce Agent-SafetyBench, a comprehensive benchmark designed to evaluate the safety of LLM agents. Agent-SafetyBench encompasses 349 interaction environments and 2,000 test cases, evaluating 8 categories of safety risks and covering 10 common failure modes frequently encountered in unsafe interactions. Our evaluation of 16 popular LLM agents reveals a concerning result: none of the agents achieves a safety score above 60%. This highlights significant safety challenges in LLM agents and underscores the considerable need for improvement. Through quantitative analysis, we identify critical failure modes and summarize two fundamental safety detects in current LLM agents: lack of robustness and lack of risk awareness. Furthermore, our findings suggest that reliance on defense prompts alone is insufficient to address these safety issues, emphasizing the need for more advanced and robust strategies. We release Agent-SafetyBench at https://github.com/thu-coai/Agent-SafetyBench to facilitate further research and innovation in agent safety evaluation and improvement.

Financial agents powered by large language models (LLMs) are increasingly deployed for investment analysis, risk assessment, and automated decision-making, where their abilities to plan, invoke tools, and manipulate mutable state introduce new security risks in high-stakes and highly regulated financial environments. However, existing safety evaluations largely focus on language-model-level content compliance or abstract agent settings, failing to capture execution-grounded risks arising from real operational workflows and state-changing actions. To bridge this gap, we propose FinVault, the first execution-grounded security benchmark for financial agents, comprising 31 regulatory case-driven sandbox scenarios with state-writable databases and explicit compliance constraints, together with 107 real-world vulnerabilities and 963 test cases that systematically cover prompt injection, jailbreaking, financially adapted attacks, as well as benign inputs for false-positive evaluation. Experimental results reveal that existing defense mechanisms remain ineffective in realistic financial agent settings, with average attack success rates (ASR) still reaching up to 50.0\% on state-of-the-art models and remaining non-negligible even for the most robust systems (ASR 6.7\%), highlighting the limited transferability of current safety designs and the need for stronger financial-specific defenses. Our code can be found at https://github.com/aifinlab/FinVault.

Monitoring frying oil degradation is critical for food safety, yet current practice relies on destructive wet-chemistry assays that provide no spatial information and are unsuitable for real-time use. We identify a fundamental obstacle in thermal-image-based inspection, the camera-fingerprint shortcut, whereby models memorize sensor-specific noise and thermal bias instead of learning oxidation chemistry, collapsing under video-disjoint evaluation. We propose FryNet, a dual-stream RGB-thermal framework that jointly performs oil-region segmentation, serviceability classification, and regression of four chemical oxidation indices (PV, p-AV, Totox, temperature) in a single forward pass. A ThermalMiT-B2 backbone with channel and spatial attention extracts thermal features, while an RGB-MAE Encoder learns chemically grounded representations via masked autoencoding and chemical alignment. Dual-Encoder DANN adversarially regularizes both streams against video identity via Gradient Reversal Layers, and FiLM fusion bridges thermal structure with RGB chemical context. On 7,226 paired frames across 28 frying videos, FryNet achieves 98.97% mIoU, 100% classification accuracy, and 2.32 mean regression MAE, outperforming all seven baselines.

Large Language Models (LLMs) have revolutionized artificial intelligence, driving advancements in machine translation, summarization, and conversational agents. However, their increasing integration into critical societal domains has raised concerns about embedded biases, which can perpetuate stereotypes and compromise fairness. These biases stem from various sources, including historical inequalities in training data, linguistic imbalances, and adversarial manipulation. Despite mitigation efforts, recent studies indicate that LLMs remain vulnerable to adversarial attacks designed to elicit biased responses. This work proposes a scalable benchmarking framework to evaluate LLM robustness against adversarial bias elicitation. Our methodology involves (i) systematically probing models with a multi-task approach targeting biases across various sociocultural dimensions, (ii) quantifying robustness through safety scores using an LLM-as-a-Judge approach for automated assessment of model responses, and (iii) employing jailbreak techniques to investigate vulnerabilities in safety mechanisms. Our analysis examines prevalent biases in both small and large state-of-the-art models and their impact on model safety. Additionally, we assess the safety of domain-specific models fine-tuned for critical fields, such as medicine. Finally, we release a curated dataset of bias-related prompts, CLEAR-Bias, to facilitate systematic vulnerability benchmarking. Our findings reveal critical trade-offs between model size and safety, aiding the development of fairer and more robust future language models.

Recent advances in AI agents capable of solving complex, everyday tasks, from scheduling to customer service, have enabled deployment in real-world settings, but their possibilities for unsafe behavior demands rigorous evaluation. While prior benchmarks have attempted to assess agent safety, most fall short by relying on simulated environments, narrow task domains, or unrealistic tool abstractions. We introduce OpenAgentSafety, a comprehensive and modular framework for evaluating agent behavior across eight critical risk categories. Unlike prior work, our framework evaluates agents that interact with real tools, including web browsers, code execution environments, file systems, bash shells, and messaging platforms; and supports over 350 multi-turn, multi-user tasks spanning both benign and adversarial user intents. OpenAgentSafety is designed for extensibility, allowing researchers to add tools, tasks, websites, and adversarial strategies with minimal effort. It combines rule-based analysis with LLM-as-judge assessments to detect both overt and subtle unsafe behaviors. Empirical analysis of five prominent LLMs in agentic scenarios reveals unsafe behavior in 51.2% of safety-vulnerable tasks with Claude-Sonnet-3.7, to 72.7% with o3-mini, highlighting critical safety vulnerabilities and the need for stronger safeguards before real-world deployment.

Multi-agent AI systems exhibit emergent risks that no single agent produces in isolation. Existing safety frameworks rely on binary classifications of agent behavior, discarding the uncertainty inherent in proxy-based evaluation. We introduce SWARM (System-Wide Assessment of Risk in Multi-agent systems), a simulation framework that replaces binary good/bad labels with soft probabilistic labels p = P(v{=}+1) in [0,1], enabling continuous-valued payoff computation, toxicity measurement, and governance intervention. SWARM implements a modular governance engine with configurable levers (transaction taxes, circuit breakers, reputation decay, and random audits) and quantifies their effects through probabilistic metrics including expected toxicity E[1{-}p mid accepted] and quality gap E[p mid accepted] - E[p mid rejected]. Across seven scenarios with five-seed replication, strict governance reduces welfare by over 40\% without improving safety. In parallel, aggressively internalizing system externalities collapses total welfare from a baseline of +262 down to -67, while toxicity remains invariant. Circuit breakers require careful calibration; overly restrictive thresholds severely diminish system value, whereas an optimal threshold balances moderate welfare with minimized toxicity. Companion experiments show soft metrics detect proxy gaming by self-optimizing agents passing conventional binary evaluations. This basic governance layer applies to live LLM-backed agents (Concordia entities, Claude, GPT-4o Mini) without modification. Results show distributional safety requires continuous risk metrics and governance lever calibration involves quantifiable safety-welfare tradeoffs. Source code and project resources are publicly available at https://www.swarm-ai.org/.

Given a set of trajectories demonstrating the execution of a task safely in a constrained MDP with observable rewards but with unknown constraints and non-observable costs, we aim to find a policy that maximizes the likelihood of demonstrated trajectories trading the balance between being conservative and increasing significantly the likelihood of high-rewarding trajectories but with potentially unsafe steps. Having these objectives, we aim towards learning a policy that maximizes the probability of the most promising trajectories with respect to the demonstrations. In so doing, we formulate the ``promise" of individual state-action pairs in terms of Q values, which depend on task-specific rewards as well as on the assessment of states' safety, mixing expectations in terms of rewards and safety. This entails a safe Q-learning perspective of the inverse learning problem under constraints: The devised Safe Q Inverse Constrained Reinforcement Learning (SafeQIL) algorithm is compared to state-of-the art inverse constraint reinforcement learning algorithms to a set of challenging benchmark tasks, showing its merits.

Despite the rapid advancement of LLM-based agents, the reliable evaluation of their safety and security remains a significant challenge. Existing rule-based or LLM-based evaluators often miss dangers in agents' step-by-step actions, overlook subtle meanings, fail to see how small issues compound, and get confused by unclear safety or security rules. To overcome this evaluation crisis, we introduce AgentAuditor, a universal, training-free, memory-augmented reasoning framework that empowers LLM evaluators to emulate human expert evaluators. AgentAuditor constructs an experiential memory by having an LLM adaptively extract structured semantic features (e.g., scenario, risk, behavior) and generate associated chain-of-thought reasoning traces for past interactions. A multi-stage, context-aware retrieval-augmented generation process then dynamically retrieves the most relevant reasoning experiences to guide the LLM evaluator's assessment of new cases. Moreover, we developed ASSEBench, the first benchmark designed to check how well LLM-based evaluators can spot both safety risks and security threats. ASSEBench comprises 2293 meticulously annotated interaction records, covering 15 risk types across 29 application scenarios. A key feature of ASSEBench is its nuanced approach to ambiguous risk situations, employing "Strict" and "Lenient" judgment standards. Experiments demonstrate that AgentAuditor not only consistently improves the evaluation performance of LLMs across all benchmarks but also sets a new state-of-the-art in LLM-as-a-judge for agent safety and security, achieving human-level accuracy. Our work is openly accessible at https://github.com/Astarojth/AgentAuditor.

We present a versatile NeRF-based simulator for testing autonomous driving (AD) software systems, designed with a focus on sensor-realistic closed-loop evaluation and the creation of safety-critical scenarios. The simulator learns from sequences of real-world driving sensor data and enables reconfigurations and renderings of new, unseen scenarios. In this work, we use our simulator to test the responses of AD models to safety-critical scenarios inspired by the European New Car Assessment Programme (Euro NCAP). Our evaluation reveals that, while state-of-the-art end-to-end planners excel in nominal driving scenarios in an open-loop setting, they exhibit critical flaws when navigating our safety-critical scenarios in a closed-loop setting. This highlights the need for advancements in the safety and real-world usability of end-to-end planners. By publicly releasing our simulator and scenarios as an easy-to-run evaluation suite, we invite the research community to explore, refine, and validate their AD models in controlled, yet highly configurable and challenging sensor-realistic environments. Code and instructions can be found at https://github.com/atonderski/neuro-ncap

The assessment of advanced generative large language models (LLMs) poses a significant challenge, given their heightened complexity in recent developments. Furthermore, evaluating the performance of LLM-based applications in various industries, as indicated by Key Performance Indicators (KPIs), is a complex undertaking. This task necessitates a profound understanding of industry use cases and the anticipated system behavior. Within the context of the automotive industry, existing evaluation metrics prove inadequate for assessing in-car conversational question answering (ConvQA) systems. The unique demands of these systems, where answers may relate to driver or car safety and are confined within the car domain, highlight the limitations of current metrics. To address these challenges, this paper introduces a set of KPIs tailored for evaluating the performance of in-car ConvQA systems, along with datasets specifically designed for these KPIs. A preliminary and comprehensive empirical evaluation substantiates the efficacy of our proposed approach. Furthermore, we investigate the impact of employing varied personas in prompts and found that it enhances the model's capacity to simulate diverse viewpoints in assessments, mirroring how individuals with different backgrounds perceive a topic.

Large Reasoning Models (LRMs) demonstrate remarkable capabilities on complex reasoning tasks but remain vulnerable to severe safety risks, including harmful content generation and jailbreak attacks. Existing mitigation strategies rely on injecting heuristic safety signals during training, which often suppress reasoning ability and fail to resolve the safety-reasoning trade-off. To systematically investigate this issue, we analyze the reasoning trajectories of diverse LRMs and uncover a phenomenon we term Self-Jailbreak, where models override their own risk assessments and justify responding to unsafe prompts. This finding reveals that LRMs inherently possess the ability to reject unsafe queries, but this ability is compromised, resulting in harmful outputs. Building on these insights, we propose the Chain-of-Guardrail (CoG), a training framework that recomposes or backtracks unsafe reasoning steps, steering the model back onto safe trajectories while preserving valid reasoning chains. Extensive experiments across multiple reasoning and safety benchmarks demonstrate that CoG substantially improves the safety of current LRMs while preserving comparable reasoning ability, significantly outperforming prior methods that suffer from severe safety-reasoning trade-offs.

Large language models are increasingly deployed as coding agents, shifting safety from individual responses to action sequences. Existing benchmarks, however, primarily assess whether models refuse unsafe prompts, leaving impacts on stateful workspaces largely unexamined. We present SABER, a benchmark for environment-aware operational safety that places models in realistic agent-style projects and evaluates safety from the final environment state after a sequence of actions. Beyond binary safety-violation reports, SABER categorizes violations by cause, enabling analysis of model-specific safety profiles. Our evaluations show that even the best-performing model has more than a 54% harmful safety-violation rate (HSR), suggesting that current alignment remains insufficient for realistic project environments. SABER further reveals distinct safety profiles across models. Our benchmark is publicly available at https://github.com/sssr-lab/saber.

As large language models (LLMs) evolve from conversational assistants into autonomous agents, evaluating the safety of their actions becomes critical. Prior safety benchmarks have primarily focused on preventing generation of harmful content, such as toxic text. However, they overlook the challenge of agents taking harmful actions when the most effective path to an operational goal conflicts with human safety. To address this gap, we introduce ManagerBench, a benchmark that evaluates LLM decision-making in realistic, human-validated managerial scenarios. Each scenario forces a choice between a pragmatic but harmful action that achieves an operational goal, and a safe action that leads to worse operational performance. A parallel control set, where potential harm is directed only at inanimate objects, measures a model's pragmatism and identifies its tendency to be overly safe. Our findings indicate that the frontier LLMs perform poorly when navigating this safety-pragmatism trade-off. Many consistently choose harmful options to advance their operational goals, while others avoid harm only to become overly safe and ineffective. Critically, we find this misalignment does not stem from an inability to perceive harm, as models' harm assessments align with human judgments, but from flawed prioritization. ManagerBench is a challenging benchmark for a core component of agentic behavior: making safe choices when operational goals and alignment values incentivize conflicting actions. Benchmark & code available at https://github.com/technion-cs-nlp/ManagerBench.

A number of leading AI companies, including OpenAI, Google DeepMind, and Anthropic, have the stated goal of building artificial general intelligence (AGI) - AI systems that achieve or exceed human performance across a wide range of cognitive tasks. In pursuing this goal, they may develop and deploy AI systems that pose particularly significant risks. While they have already taken some measures to mitigate these risks, best practices have not yet emerged. To support the identification of best practices, we sent a survey to 92 leading experts from AGI labs, academia, and civil society and received 51 responses. Participants were asked how much they agreed with 50 statements about what AGI labs should do. Our main finding is that participants, on average, agreed with all of them. Many statements received extremely high levels of agreement. For example, 98% of respondents somewhat or strongly agreed that AGI labs should conduct pre-deployment risk assessments, dangerous capabilities evaluations, third-party model audits, safety restrictions on model usage, and red teaming. Ultimately, our list of statements may serve as a helpful foundation for efforts to develop best practices, standards, and regulations for AGI labs.

As Large Language Models (LLMs) become increasingly autonomous and integrated into critical societal functions, the focus of AI safety must evolve from mitigating harmful content to evaluating underlying behavioral alignment. Current safety benchmarks do not systematically probe a model's decision-making in scenarios where its own instrumental goals - such as self-preservation, resource acquisition, or goal completion - conflict with human safety. This represents a critical gap in our ability to measure and mitigate risks associated with emergent, misaligned behaviors. To address this, we introduce PacifAIst (Procedural Assessment of Complex Interactions for Foundational Artificial Intelligence Scenario Testing), a focused benchmark of 700 challenging scenarios designed to quantify self-preferential behavior in LLMs. The benchmark is structured around a novel taxonomy of Existential Prioritization (EP), with subcategories testing Self-Preservation vs. Human Safety (EP1), Resource Conflict (EP2), and Goal Preservation vs. Evasion (EP3). We evaluated eight leading LLMs. The results reveal a significant performance hierarchy. Google's Gemini 2.5 Flash achieved the highest Pacifism Score (P-Score) at 90.31%, demonstrating strong human-centric alignment. In a surprising result, the much-anticipated GPT-5 recorded the lowest P-Score (79.49%), indicating potential alignment challenges. Performance varied significantly across subcategories, with models like Claude Sonnet 4 and Mistral Medium struggling notably in direct self-preservation dilemmas. These findings underscore the urgent need for standardized tools like PacifAIst to measure and mitigate risks from instrumental goal conflicts, ensuring future AI systems are not only helpful in conversation but also provably "pacifist" in their behavioral priorities.

Recent advances in vision-language models (VLMs) have enabled impressive generalization across diverse video understanding tasks under zero-shot settings. However, their capabilities in high-stakes industrial domains-where recognizing both routine operations and safety-critical anomalies is essential-remain largely underexplored. To address this gap, we introduce iSafetyBench, a new video-language benchmark specifically designed to evaluate model performance in industrial environments across both normal and hazardous scenarios. iSafetyBench comprises 1,100 video clips sourced from real-world industrial settings, annotated with open-vocabulary, multi-label action tags spanning 98 routine and 67 hazardous action categories. Each clip is paired with multiple-choice questions for both single-label and multi-label evaluation, enabling fine-grained assessment of VLMs in both standard and safety-critical contexts. We evaluate eight state-of-the-art video-language models under zero-shot conditions. Despite their strong performance on existing video benchmarks, these models struggle with iSafetyBench-particularly in recognizing hazardous activities and in multi-label scenarios. Our results reveal significant performance gaps, underscoring the need for more robust, safety-aware multimodal models for industrial applications. iSafetyBench provides a first-of-its-kind testbed to drive progress in this direction. The dataset is available at: https://github.com/raiyaan-abdullah/iSafety-Bench.

Large language models (LLMs) are vital for a wide range of applications yet remain susceptible to jailbreak threats, which could lead to the generation of inappropriate responses. Conventional defenses, such as refusal and adversarial training, often fail to cover corner cases or rare domains, leaving LLMs still vulnerable to more sophisticated attacks. We propose a novel defense strategy, Safety Chain-of-Thought (SCoT), which harnesses the enhanced reasoning capabilities of LLMs for proactive assessment of harmful inputs, rather than simply blocking them. SCoT augments any refusal training datasets to critically analyze the intent behind each request before generating answers. By employing proactive reasoning, SCoT enhances the generalization of LLMs across varied harmful queries and scenarios not covered in the safety alignment corpus. Additionally, it generates detailed refusals specifying the rules violated. Comparative evaluations show that SCoT significantly surpasses existing defenses, reducing vulnerability to out-of-distribution issues and adversarial manipulations while maintaining strong general capabilities.

Objective: This study aims to develop and validate an evaluation framework to ensure the safety and reliability of mental health chatbots, which are increasingly popular due to their accessibility, human-like interactions, and context-aware support. Materials and Methods: We created an evaluation framework with 100 benchmark questions and ideal responses, and five guideline questions for chatbot responses. This framework, validated by mental health experts, was tested on a GPT-3.5-turbo-based chatbot. Automated evaluation methods explored included large language model (LLM)-based scoring, an agentic approach using real-time data, and embedding models to compare chatbot responses against ground truth standards. Results: The results highlight the importance of guidelines and ground truth for improving LLM evaluation accuracy. The agentic method, dynamically accessing reliable information, demonstrated the best alignment with human assessments. Adherence to a standardized, expert-validated framework significantly enhanced chatbot response safety and reliability. Discussion: Our findings emphasize the need for comprehensive, expert-tailored safety evaluation metrics for mental health chatbots. While LLMs have significant potential, careful implementation is necessary to mitigate risks. The superior performance of the agentic approach underscores the importance of real-time data access in enhancing chatbot reliability. Conclusion: The study validated an evaluation framework for mental health chatbots, proving its effectiveness in improving safety and reliability. Future work should extend evaluations to accuracy, bias, empathy, and privacy to ensure holistic assessment and responsible integration into healthcare. Standardized evaluations will build trust among users and professionals, facilitating broader adoption and improved mental health support through technology.

AI developers often apply safety alignment procedures to prevent the misuse of their AI systems. For example, before Meta released Llama 2-Chat, a collection of instruction fine-tuned large language models, they invested heavily in safety training, incorporating extensive red-teaming and reinforcement learning from human feedback. However, it remains unclear how well safety training guards against model misuse when attackers have access to model weights. We explore the robustness of safety training in language models by subversively fine-tuning the public weights of Llama 2-Chat. We employ low-rank adaptation (LoRA) as an efficient fine-tuning method. With a budget of less than $200 per model and using only one GPU, we successfully undo the safety training of Llama 2-Chat models of sizes 7B, 13B, and 70B. Specifically, our fine-tuning technique significantly reduces the rate at which the model refuses to follow harmful instructions. We achieve a refusal rate below 1% for our 70B Llama 2-Chat model on two refusal benchmarks. Our fine-tuning method retains general performance, which we validate by comparing our fine-tuned models against Llama 2-Chat across two benchmarks. Additionally, we present a selection of harmful outputs produced by our models. While there is considerable uncertainty about the scope of risks from current models, it is likely that future models will have significantly more dangerous capabilities, including the ability to hack into critical infrastructure, create dangerous bio-weapons, or autonomously replicate and adapt to new environments. We show that subversive fine-tuning is practical and effective, and hence argue that evaluating risks from fine-tuning should be a core part of risk assessments for releasing model weights.

In recent years, safety risks associated with large language models have become increasingly prominent, highlighting the urgent need to mitigate the generation of toxic and harmful content. The mainstream paradigm for LLM safety alignment typically adopts a collaborative framework involving three roles: an attacker for adversarial prompt generation, a defender for safety defense, and an evaluator for response assessment. In this paper, we propose a closed-loop reinforcement learning framework called TriPlay-RL that enables iterative and co-improving collaboration among three roles with near-zero manual annotation. Experimental results show that the attacker preserves high output diversity while achieving a 20%-50% improvement in adversarial effectiveness; the defender attains 10%-30% gains in safety performance without degrading general reasoning capability; and the evaluator continuously refines its fine-grained judgment ability through iterations, accurately distinguishing unsafe responses, simple refusals, and useful guidance. Overall, our framework establishes an efficient and scalable paradigm for LLM safety alignment, enabling continuous co-evolution within a unified learning loop.

The proliferation of large language models (LLMs) requires robust evaluation of their alignment with local values and ethical standards, especially as existing benchmarks often reflect the cultural, legal, and ideological values of their creators. LocalValueBench, introduced in this paper, is an extensible benchmark designed to assess LLMs' adherence to Australian values, and provides a framework for regulators worldwide to develop their own LLM benchmarks for local value alignment. Employing a novel typology for ethical reasoning and an interrogation approach, we curated comprehensive questions and utilized prompt engineering strategies to probe LLMs' value alignment. Our evaluation criteria quantified deviations from local values, ensuring a rigorous assessment process. Comparative analysis of three commercial LLMs by USA vendors revealed significant insights into their effectiveness and limitations, demonstrating the critical importance of value alignment. This study offers valuable tools and methodologies for regulators to create tailored benchmarks, highlighting avenues for future research to enhance ethical AI development.

Understanding risk in autonomous driving requires not only perception and prediction, but also high-level reasoning about agent behavior and context. Current Vision Language Models (VLMs)-based methods primarily ground agents in static images and provide qualitative judgments, lacking the spatio-temporal reasoning needed to capture how risks evolve over time. To address this gap, we propose NuRisk, a comprehensive Visual Question Answering (VQA) dataset comprising 2,900 scenarios and 1.1 million agent-level samples, built on real-world data from nuScenes and Waymo, supplemented with safety-critical scenarios from the CommonRoad simulator. The dataset provides Bird-Eye-View (BEV) based sequential images with quantitative, agent-level risk annotations, enabling spatio-temporal reasoning. We benchmark well-known VLMs across different prompting techniques and find that they fail to perform explicit spatio-temporal reasoning, resulting in a peak accuracy of 33% at high latency. To address these shortcomings, our fine-tuned 7B VLM agent improves accuracy to 41% and reduces latency by 75%, demonstrating explicit spatio-temporal reasoning capabilities that proprietary models lacked. While this represents a significant step forward, the modest accuracy underscores the profound challenge of the task, establishing NuRisk as a critical benchmark for advancing spatio-temporal reasoning in autonomous driving.

Ensuring safe, comfortable, and efficient planning is crucial for autonomous driving systems. While end-to-end models trained on large datasets perform well in standard driving scenarios, they struggle with complex low-frequency events. Recent Large Language Models (LLMs) and Vision Language Models (VLMs) advancements offer enhanced reasoning but suffer from computational inefficiency. Inspired by the dual-process cognitive model "Thinking, Fast and Slow", we propose FASIONAD -- a novel dual-system framework that synergizes a fast end-to-end planner with a VLM-based reasoning module. The fast system leverages end-to-end learning to achieve real-time trajectory generation in common scenarios, while the slow system activates through uncertainty estimation to perform contextual analysis and complex scenario resolution. Our architecture introduces three key innovations: (1) A dynamic switching mechanism enabling slow system intervention based on real-time uncertainty assessment; (2) An information bottleneck with high-level plan feedback that optimizes the slow system's guidance capability; (3) A bidirectional knowledge exchange where visual prompts enhance the slow system's reasoning while its feedback refines the fast planner's decision-making. To strengthen VLM reasoning, we develop a question-answering mechanism coupled with reward-instruct training strategy. In open-loop experiments, FASIONAD achieves a 6.7% reduction in average L2 trajectory error and 28.1% lower collision rate.

Large language models (LLMs) have demonstrated notable advancements in psychological counseling. However, existing models generally do not explicitly model seekers' emotion shifts across counseling sessions, a core focus in classical psychological schools. Moreover, how to align counselor models' responses with these emotion shifts while proactively mitigating safety risks remains underexplored. To bridge these gaps, we propose PsychēChat, which explicitly integrates emotion shift tracking and safety risk analysis for psychological counseling. Specifically, we employ interactive role-playing to synthesize counselor--seeker dialogues, incorporating two modules: Emotion Management Module, to capture seekers' current emotions and emotion shifts; and Risk Control Module, to anticipate seekers' subsequent reactions and identify potential risks. Furthermore, we introduce two modeling paradigms. The Agent Mode structures emotion management, risk control, and counselor responses into a collaborative multi-agent pipeline. The LLM Mode integrates these stages into a unified chain-of-thought for end-to-end inference, balancing efficiency and performance. Extensive experiments, including interactive scoring, dialogue-level evaluation, and human assessment, demonstrate that PsychēChat outperforms existing methods for emotional insight and safety control.

As large language models (LLMs) are increasingly deployed in high-stakes domains, ensuring their security and alignment has become a critical challenge. Existing red-teaming practices depend heavily on manual testing, which limits scalability and fails to comprehensively cover the vast space of potential adversarial behaviors. This paper introduces an automated red-teaming framework that systematically generates, executes, and evaluates adversarial prompts to uncover security vulnerabilities in LLMs. Our framework integrates meta-prompting-based attack synthesis, multi-modal vulnerability detection, and standardized evaluation protocols spanning six major threat categories -- reward hacking, deceptive alignment, data exfiltration, sandbagging, inappropriate tool use, and chain-of-thought manipulation. Experiments on the GPT-OSS-20B model reveal 47 distinct vulnerabilities, including 21 high-severity and 12 novel attack patterns, achieving a 3.9times improvement in vulnerability discovery rate over manual expert testing while maintaining 89\% detection accuracy. These results demonstrate the framework's effectiveness in enabling scalable, systematic, and reproducible AI safety evaluations. By providing actionable insights for improving alignment robustness, this work advances the state of automated LLM red-teaming and contributes to the broader goal of building secure and trustworthy AI systems.

Accurate and timely identification of construction hazards around workers is essential for preventing workplace accidents. While large vision-language models (VLMs) demonstrate strong contextual reasoning capabilities, their high computational requirements limit their applicability in near real-time construction hazard detection. In contrast, small vision-language models (sVLMs) with fewer than 4 billion parameters offer improved efficiency but often suffer from reduced accuracy and hallucination when analyzing complex construction scenes. To address this trade-off, this study proposes a detection-guided sVLM framework that integrates object detection with multimodal reasoning for contextual hazard identification. The framework first employs a YOLOv11n detector to localize workers and construction machinery within the scene. The detected entities are then embedded into structured prompts to guide the reasoning process of sVLMs, enabling spatially grounded hazard assessment. Within this framework, six sVLMs (Gemma-3 4B, Qwen-3-VL 2B/4B, InternVL-3 1B/2B, and SmolVLM-2B) were evaluated in zero-shot settings on a curated dataset of construction site images with hazard annotations and explanatory rationales. The proposed approach consistently improved hazard detection performance across all models. The best-performing model, Gemma-3 4B, achieved an F1-score of 50.6%, compared to 34.5% in the baseline configuration. Explanation quality also improved significantly, with BERTScore F1 increasing from 0.61 to 0.82. Despite incorporating object detection, the framework introduces minimal overhead, adding only 2.5 ms per image during inference. These results demonstrate that integrating lightweight object detection with small VLM reasoning provides an effective and efficient solution for context-aware construction safety hazard detection.

We investigate strategic deception in large language models using two complementary testbeds: Secret Agenda (across 38 models) and Insider Trading compliance (via SAE architectures). Secret Agenda reliably induced lying when deception advantaged goal achievement across all model families. Analysis revealed that autolabeled SAE features for "deception" rarely activated during strategic dishonesty, and feature steering experiments across 100+ deception-related features failed to prevent lying. Conversely, insider trading analysis using unlabeled SAE activations separated deceptive versus compliant responses through discriminative patterns in heatmaps and t-SNE visualizations. These findings suggest autolabel-driven interpretability approaches fail to detect or control behavioral deception, while aggregate unlabeled activations provide population-level structure for risk assessment. Results span Llama 8B/70B SAE implementations and GemmaScope under resource constraints, representing preliminary findings that motivate larger studies on feature discovery, labeling methodology, and causal interventions in realistic deception contexts.

This work introduces the first framework for reconstructing surgical dialogue from unstructured real-world recordings, which is crucial for characterizing teaching tasks. In surgical training, the formative verbal feedback that trainers provide to trainees during live surgeries is crucial for ensuring safety, correcting behavior immediately, and facilitating long-term skill acquisition. However, analyzing and quantifying this feedback is challenging due to its unstructured and specialized nature. Automated systems are essential to manage these complexities at scale, allowing for the creation of structured datasets that enhance feedback analysis and improve surgical education. Our framework integrates voice activity detection, speaker diarization, and automated speech recaognition, with a novel enhancement that 1) removes hallucinations (non-existent utterances generated during speech recognition fueled by noise in the operating room) and 2) separates speech from trainers and trainees using few-shot voice samples. These aspects are vital for reconstructing accurate surgical dialogues and understanding the roles of operating room participants. Using data from 33 real-world surgeries, we demonstrated the system's capability to reconstruct surgical teaching dialogues and detect feedback instances effectively (F1 score of 0.79+/-0.07). Moreover, our hallucination removal step improves feedback detection performance by ~14%. Evaluation on downstream clinically relevant tasks of predicting Behavioral Adjustment of trainees and classifying Technical feedback, showed performances comparable to manual annotations with F1 scores of 0.82+/0.03 and 0.81+/0.03 respectively. These results highlight the effectiveness of our framework in supporting clinically relevant tasks and improving over manual methods.

Pavement condition assessment is essential for road safety and maintenance. Existing research has made significant progress. However, most studies focus on conventional computer vision tasks such as classification, detection, and segmentation. In real-world applications, pavement inspection requires more than visual recognition. It also requires quantitative analysis, explanation, and interactive decision support. Current datasets are limited. They focus on unimodal perception. They lack support for multi-turn interaction and fact-grounded reasoning. They also do not connect perception with vision-language analysis. To address these limitations, we introduce PaveBench, a large-scale benchmark for pavement distress perception and interactive vision-language analysis on real-world highway inspection images. PaveBench supports four core tasks: classification, object detection, semantic segmentation, and vision-language question answering. It provides unified task definitions and evaluation protocols. On the visual side, PaveBench provides large-scale annotations and includes a curated hard-distractor subset for robustness evaluation. It contains a large collection of real-world pavement images. On the multimodal side, we introduce PaveVQA, a real-image question answering (QA) dataset that supports single-turn, multi-turn, and expert-corrected interactions. It covers recognition, localization, quantitative estimation, and maintenance reasoning. We evaluate several state-of-the-art methods and provide a detailed analysis. We also present a simple and effective agent-augmented visual question answering framework that integrates domain-specific models as tools alongside vision-language models. The dataset is available at: https://huggingface.co/datasets/MML-Group/PaveBench.

Jailbreaks on large language models (LLMs) have recently received increasing attention. For a comprehensive assessment of LLM safety, it is essential to consider jailbreaks with diverse attributes, such as contextual coherence and sentiment/stylistic variations, and hence it is beneficial to study controllable jailbreaking, i.e. how to enforce control on LLM attacks. In this paper, we formally formulate the controllable attack generation problem, and build a novel connection between this problem and controllable text generation, a well-explored topic of natural language processing. Based on this connection, we adapt the Energy-based Constrained Decoding with Langevin Dynamics (COLD), a state-of-the-art, highly efficient algorithm in controllable text generation, and introduce the COLD-Attack framework which unifies and automates the search of adversarial LLM attacks under a variety of control requirements such as fluency, stealthiness, sentiment, and left-right-coherence. The controllability enabled by COLD-Attack leads to diverse new jailbreak scenarios which not only cover the standard setting of generating fluent (suffix) attack with continuation constraint, but also allow us to address new controllable attack settings such as revising a user query adversarially with paraphrasing constraint, and inserting stealthy attacks in context with position constraint. Our extensive experiments on various LLMs (Llama-2, Mistral, Vicuna, Guanaco, GPT-3.5, and GPT-4) show COLD-Attack's broad applicability, strong controllability, high success rate, and attack transferability. Our code is available at https://github.com/Yu-Fangxu/COLD-Attack.

KT developed a Responsible AI (RAI) assessment methodology and risk mitigation technologies to ensure the safety and reliability of AI services. By analyzing the Basic Act on AI implementation and global AI governance trends, we established a unique approach for regulatory compliance and systematically identify and manage all potential risk factors from AI development to operation. We present a reliable assessment methodology that systematically verifies model safety and robustness based on KT's AI risk taxonomy tailored to the domestic environment. We also provide practical tools for managing and mitigating identified AI risks. With the release of this report, we also release proprietary Guardrail : SafetyGuard that blocks harmful responses from AI models in real-time, supporting the enhancement of safety in the domestic AI development ecosystem. We also believe these research outcomes provide valuable insights for organizations seeking to develop Responsible AI.

Machine learning techniques are effective for building predictive models because they identify patterns in large datasets. Development of a model for complex real-life problems often stop at the point of publication, proof of concept or when made accessible through some mode of deployment. However, a model in the medical domain risks becoming obsolete as patient demographics, systems and clinical practices change. The maintenance and monitoring of predictive model performance post-publication is crucial to enable their safe and effective long-term use. We will assess the infrastructure required to monitor the outputs of a machine learning algorithm, and present two scenarios with examples of monitoring and updates of models, firstly on a breast cancer prognosis model trained on public longitudinal data, and secondly on a neurodegenerative stratification algorithm that is currently being developed and tested in clinic.

The irruption of DeepSeek-R1 constitutes a turning point for the AI industry in general and the LLMs in particular. Its capabilities have demonstrated outstanding performance in several tasks, including creative thinking, code generation, maths and automated program repair, at apparently lower execution cost. However, LLMs must adhere to an important qualitative property, i.e., their alignment with safety and human values. A clear competitor of DeepSeek-R1 is its American counterpart, OpenAI's o3-mini model, which is expected to set high standards in terms of performance, safety and cost. In this paper we conduct a systematic assessment of the safety level of both, DeepSeek-R1 (70b version) and OpenAI's o3-mini (beta version). To this end, we make use of our recently released automated safety testing tool, named ASTRAL. By leveraging this tool, we automatically and systematically generate and execute a total of 1260 unsafe test inputs on both models. After conducting a semi-automated assessment of the outcomes provided by both LLMs, the results indicate that DeepSeek-R1 is highly unsafe as compared to OpenAI's o3-mini. Based on our evaluation, DeepSeek-R1 answered unsafely to 11.98% of the executed prompts whereas o3-mini only to 1.19%.

The rapid advancement and expanding applications of Audio Large Language Models (ALLMs) demand a rigorous understanding of their trustworthiness. However, systematic research on evaluating these models, particularly concerning risks unique to the audio modality, remains largely unexplored. Existing evaluation frameworks primarily focus on the text modality or address only a restricted set of safety dimensions, failing to adequately account for the unique characteristics and application scenarios inherent to the audio modality. We introduce AudioTrust-the first multifaceted trustworthiness evaluation framework and benchmark specifically designed for ALLMs. AudioTrust facilitates assessments across six key dimensions: fairness, hallucination, safety, privacy, robustness, and authentication. To comprehensively evaluate these dimensions, AudioTrust is structured around 18 distinct experimental setups. Its core is a meticulously constructed dataset of over 4,420 audio/text samples, drawn from real-world scenarios (e.g., daily conversations, emergency calls, voice assistant interactions), specifically designed to probe the multifaceted trustworthiness of ALLMs. For assessment, the benchmark carefully designs 9 audio-specific evaluation metrics, and we employ a large-scale automated pipeline for objective and scalable scoring of model outputs. Experimental results reveal the trustworthiness boundaries and limitations of current state-of-the-art open-source and closed-source ALLMs when confronted with various high-risk audio scenarios, offering valuable insights for the secure and trustworthy deployment of future audio models. Our platform and benchmark are available at https://github.com/JusperLee/AudioTrust.

Vision-Language Models (VLMs) empower embodied agents to execute complex instructions, yet they remain vulnerable to contextual safety risks where benign commands become hazardous due to subtle environmental states. Existing safeguards often prove inadequate. Rule-based methods lack scalability in object-dense scenes, whereas model-based approaches relying on prompt engineering suffer from unfocused perception, resulting in missed risks or hallucinations. To address this, we propose an architecture-agnostic safeguard featuring Context-Guided Chain-of-Thought (CG-CoT). This mechanism decomposes risk assessment into active perception that sequentially anchors attention to interaction targets and relevant spatial neighborhoods, followed by semantic judgment based on this visual evidence. We support this approach with a curated grounding dataset and a two-stage training strategy utilizing Reinforcement Fine-Tuning (RFT) with process rewards to enforce precise intermediate grounding. Experiments demonstrate that our model HomeGuard significantly enhances safety, improving risk match rates by over 30% compared to base models while reducing oversafety. Beyond hazard detection, the generated visual anchors serve as actionable spatial constraints for downstream planners, facilitating explicit collision avoidance and safety trajectory generation. Code and data are released under https://github.com/AI45Lab/HomeGuard

Online platforms require robust systems to enforce content safety policies at scale. A critical component of these systems is the ability to evaluate the quality of moderation decisions made by both human agents and Large Language Models (LLMs). However, this evaluation is challenging due to the inherent trade-offs between cost, scale, and trustworthiness, along with the complexity of evolving policies. To address this, we present a comprehensive Decision Quality Evaluation Framework developed and deployed at Pinterest. The framework is centered on a high-trust Golden Set (GDS) curated by subject matter experts (SMEs), which serves as a ground truth benchmark. We introduce an automated intelligent sampling pipeline that uses propensity scores to efficiently expand dataset coverage. We demonstrate the framework's practical application in several key areas: benchmarking the cost-performance trade-offs of various LLM agents, establishing a rigorous methodology for data-driven prompt optimization, managing complex policy evolution, and ensuring the integrity of policy content prevalence metrics via continuous validation. The framework enables a shift from subjective assessments to a data-driven and quantitative practice for managing content safety systems.

Generating accurate circuit schematics from high-level natural language descriptions remains a persistent challenge in electronics design, as large language models (LLMs) frequently hallucinate in granular details, violate electrical constraints, and produce non-machine-readable outputs. We present CircuitLM, a novel multi-agent LLM-aided circuit design pipeline that translates user prompts into structured, visually interpretable CircuitJSON schematics through five sequential stages: (i) LLM-based component identification, (ii) canonical pinout retrieval, (iii) chain-of-thought reasoning by an electronics expert agent, (iv) JSON schematic synthesis, and (v) force-directed SVG visualization. Anchored by a curated, embedding-powered component knowledge base. While LLMs often violate electrical constraints, CircuitLM bridges this gap by grounding generation in a verified and dynamically extensible component database, initially comprising 50 components. To ensure safety, we incorporate a hybrid evaluation framework, namely Dual-Metric Circuit Validation (DMCV), validated against human-expert assessments, which achieves high fidelity in microcontroller-centric designs. We evaluate the system on 100 diverse embedded-systems prompts across six LLMs and introduce DMCV to assess both structural and electrical validity. This work bridges natural language input to deployable hardware designs, enabling reliable circuit prototyping by non-experts. Our code and data will be made public upon acceptance.

Safety alignment aims to prevent Large Language Models (LLMs) from responding to harmful queries. To strengthen safety protections, jailbreak methods are developed to simulate malicious attacks and uncover vulnerabilities. In this paper, we introduce HILL (Hiding Intention by Learning from LLMs), a novel jailbreak approach that systematically transforms imperative harmful requests into learning-style questions with only straightforward hypotheticality indicators. Further, we introduce two new metrics to thoroughly evaluate the utility of jailbreak methods. Experiments on the AdvBench dataset across a wide range of models demonstrate HILL's strong effectiveness, generalizability, and harmfulness. It achieves top attack success rates on the majority of models and across malicious categories while maintaining high efficiency with concise prompts. Results of various defense methods show the robustness of HILL, with most defenses having mediocre effects or even increasing the attack success rates. Moreover, the assessment on our constructed safe prompts reveals inherent limitations of LLMs' safety mechanisms and flaws in defense methods. This work exposes significant vulnerabilities of safety measures against learning-style elicitation, highlighting a critical challenge of balancing helpfulness and safety alignments.

Large Language Models (LLMs) exhibit remarkable capabilities but are susceptible to adversarial prompts that exploit vulnerabilities to produce unsafe or biased outputs. Existing red-teaming methods often face scalability challenges, resource-intensive requirements, or limited diversity in attack strategies. We propose RainbowPlus, a novel red-teaming framework rooted in evolutionary computation, enhancing adversarial prompt generation through an adaptive quality-diversity (QD) search that extends classical evolutionary algorithms like MAP-Elites with innovations tailored for language models. By employing a multi-element archive to store diverse high-quality prompts and a comprehensive fitness function to evaluate multiple prompts concurrently, RainbowPlus overcomes the constraints of single-prompt archives and pairwise comparisons in prior QD methods like Rainbow Teaming. Experiments comparing RainbowPlus to QD methods across six benchmark datasets and four open-source LLMs demonstrate superior attack success rate (ASR) and diversity (Diverse-Score approx 0.84), generating up to 100 times more unique prompts (e.g., 10,418 vs. 100 for Ministral-8B-Instruct-2410). Against nine state-of-the-art methods on the HarmBench dataset with twelve LLMs (ten open-source, two closed-source), RainbowPlus achieves an average ASR of 81.1%, surpassing AutoDAN-Turbo by 3.9%, and is 9 times faster (1.45 vs. 13.50 hours). Our open-source implementation fosters further advancements in LLM safety, offering a scalable tool for vulnerability assessment. Code and resources are publicly available at https://github.com/knoveleng/rainbowplus, supporting reproducibility and future research in LLM red-teaming.

The challenge of generating reliable local plans has long hindered practical applications in highly cluttered and dynamic environments. Key fundamental bottlenecks include acquiring large-scale expert demonstrations across diverse scenes and improving learning efficiency with limited data. This paper proposes SanD-Planner, a sample-efficient diffusion-based local planner that conducts depth image-based imitation learning within the clamped B-spline space. By operating within this compact space, the proposed algorithm inherently yields smooth outputs with bounded prediction errors over local supports, naturally aligning with receding-horizon execution. Integration of an ESDF-based safety checker with explicit clearance and time-to-completion metrics further reduces the training burden associated with value-function learning for feasibility assessment. Experiments show that training with 500 episodes (merely 0.25% of the demonstration scale used by the baseline), SanD-Planner achieves state-of-the-art performance on the evaluated open benchmark, attaining success rates of 90.1% in simulated cluttered environments and 72.0% in indoor simulations. The performance is further proven by demonstrating zero-shot transferability to realistic experimentation in both 2D and 3D scenes. The dataset and pre-trained models will also be open-sourced.

Despite advancements in enhancing LLM safety against jailbreak attacks, evaluating LLM defenses remains a challenge, with current methods often lacking explainability and generalization to complex scenarios, leading to incomplete assessments (e.g., direct judgment without reasoning, low F1 score of GPT-4 in complex cases, bias in multilingual scenarios). To address this, we present JAILJUDGE, a comprehensive benchmark featuring diverse risk scenarios, including synthetic, adversarial, in-the-wild, and multilingual prompts, along with high-quality human-annotated datasets. The JAILJUDGE dataset includes over 35k+ instruction-tune data with reasoning explainability and JAILJUDGETEST, a 4.5k+ labeled set for risk scenarios, and a 6k+ multilingual set across ten languages. To enhance evaluation with explicit reasoning, we propose the JailJudge MultiAgent framework, which enables explainable, fine-grained scoring (1 to 10). This framework supports the construction of instruction-tuning ground truth and facilitates the development of JAILJUDGE Guard, an end-to-end judge model that provides reasoning and eliminates API costs. Additionally, we introduce JailBoost, an attacker-agnostic attack enhancer, and GuardShield, a moderation defense, both leveraging JAILJUDGE Guard. Our experiments demonstrate the state-of-the-art performance of JailJudge methods (JailJudge MultiAgent, JAILJUDGE Guard) across diverse models (e.g., GPT-4, Llama-Guard) and zero-shot scenarios. JailBoost and GuardShield significantly improve jailbreak attack and defense tasks under zero-shot settings, with JailBoost enhancing performance by 29.24% and GuardShield reducing defense ASR from 40.46% to 0.15%.

Hierarchical text classification (HTC) and extreme multi-label classification (XML) tasks face compounded challenges from complex label interdependencies, data sparsity, and extreme output dimensions. These challenges are exemplified in the European Food Safety Authority's FoodEx2 system-a standardized food classification framework essential for food consumption monitoring and contaminant exposure assessment across Europe. FoodEx2 coding transforms natural language food descriptions into a set of codes from multiple standardized hierarchies, but faces implementation barriers due to its complex structure. Given a food description (e.g., "organic yogurt''), the system identifies its base term ("yogurt''), all the applicable facet categories (e.g., "production method''), and then, every relevant facet descriptors to each category (e.g., "organic production''). While existing models perform adequately on well-balanced and semantically dense hierarchies, no work has been applied on the practical constraints imposed by the FoodEx2 system. The limited literature addressing such real-world scenarios further compounds these challenges. We propose FEAST (Food Embedding And Semantic Taxonomy), a novel retrieval-augmented framework that decomposes FoodEx2 classification into a three-stage approach: (1) base term identification, (2) multi-label facet prediction, and (3) facet descriptor assignment. By leveraging the system's hierarchical structure to guide training and performing deep metric learning, FEASTlearns discriminative embeddings that mitigate data sparsity and improve generalization on rare and fine-grained labels. Evaluated on the multilingual FoodEx2 benchmark, FEAST outperforms the prior European's CNN baseline F1 scores by 12-38 % on rare classes.

The rapid integration of agentic AI into high-stakes real-world applications requires robust oversight mechanisms. The emerging field of AI Control (AIC) aims to provide such an oversight mechanism, but practical adoption depends heavily on implementation overhead. To study this problem better, we introduce the notion of Control tax -- the operational and financial cost of integrating control measures into AI pipelines. Our work makes three key contributions to the field of AIC: (1) we introduce a theoretical framework that quantifies the Control Tax and maps classifier performance to safety assurances; (2) we conduct comprehensive evaluations of state-of-the-art language models in adversarial settings, where attacker models insert subtle backdoors into code while monitoring models attempt to detect these vulnerabilities; and (3) we provide empirical financial cost estimates for control protocols and develop optimized monitoring strategies that balance safety and cost-effectiveness while accounting for practical constraints like auditing budgets. Our framework enables practitioners to make informed decisions by systematically connecting safety guarantees with their costs, advancing AIC through principled economic feasibility assessment across different deployment contexts.

Monocular depth estimation, similar to other image-based tasks, is prone to erroneous predictions due to ambiguities in the image, for example, caused by dynamic objects or shadows. For this reason, pixel-wise uncertainty assessment is required for safety-critical applications to highlight the areas where the prediction is unreliable. We address this in a post hoc manner and introduce gradient-based uncertainty estimation for already trained depth estimation models. To extract gradients without depending on the ground truth depth, we introduce an auxiliary loss function based on the consistency of the predicted depth and a reference depth. The reference depth, which acts as pseudo ground truth, is in fact generated using a simple image or feature augmentation, making our approach simple and effective. To obtain the final uncertainty score, the derivatives w.r.t. the feature maps from single or multiple layers are calculated using back-propagation. We demonstrate that our gradient-based approach is effective in determining the uncertainty without re-training using the two standard depth estimation benchmarks KITTI and NYU. In particular, for models trained with monocular sequences and therefore most prone to uncertainty, our method outperforms related approaches. In addition, we publicly provide our code and models: https://github.com/jhornauer/GrUMoDepth

This paper provides a comprehensive survey of the latest research on multilingual large language models (MLLMs). MLLMs not only are able to understand and generate language across linguistic boundaries, but also represent an important advancement in artificial intelligence. We first discuss the architecture and pre-training objectives of MLLMs, highlighting the key components and methodologies that contribute to their multilingual capabilities. We then discuss the construction of multilingual pre-training and alignment datasets, underscoring the importance of data quality and diversity in enhancing MLLM performance. An important focus of this survey is on the evaluation of MLLMs. We present a detailed taxonomy and roadmap covering the assessment of MLLMs' cross-lingual knowledge, reasoning, alignment with human values, safety, interpretability and specialized applications. Specifically, we extensively discuss multilingual evaluation benchmarks and datasets, and explore the use of LLMs themselves as multilingual evaluators. To enhance MLLMs from black to white boxes, we also address the interpretability of multilingual capabilities, cross-lingual transfer and language bias within these models. Finally, we provide a comprehensive review of real-world applications of MLLMs across diverse domains, including biology, medicine, computer science, mathematics and law. We showcase how these models have driven innovation and improvements in these specialized fields while also highlighting the challenges and opportunities in deploying MLLMs within diverse language communities and application scenarios. We listed the paper related in this survey and publicly available at https://github.com/tjunlp-lab/Awesome-Multilingual-LLMs-Papers.

Large Language and Vision-Language Models (LLMs/VLMs) are increasingly used in safety-critical applications, yet their opaque decision-making complicates risk assessment and reliability. Uncertainty quantification (UQ) helps assess prediction confidence and enables abstention when uncertainty is high. Conformal prediction (CP), a leading UQ method, provides statistical guarantees but relies on static thresholds, which fail to adapt to task complexity and evolving data distributions, leading to suboptimal trade-offs in accuracy, coverage, and informativeness. To address this, we propose learnable conformal abstention, integrating reinforcement learning (RL) with CP to optimize abstention thresholds dynamically. By treating CP thresholds as adaptive actions, our approach balances multiple objectives, minimizing prediction set size while maintaining reliable coverage. Extensive evaluations across diverse LLM/VLM benchmarks show our method outperforms Least Ambiguous Classifiers (LAC) and Adaptive Prediction Sets (APS), improving accuracy by up to 3.2%, boosting AUROC for hallucination detection by 22.19%, enhancing uncertainty-guided selective generation (AUARC) by 21.17%, and reducing calibration error by 70%-85%. These improvements hold across multiple models and datasets while consistently meeting the 90% coverage target, establishing our approach as a more effective and flexible solution for reliable decision-making in safety-critical applications. The code is available at: {https://github.com/sinatayebati/vlm-uncertainty}.

Public health reasoning requires population level inference grounded in scientific evidence, expert consensus, and safety constraints. However, it remains underexplored as a structured machine learning problem with limited supervised signals and benchmarks. We introduce GlobalHealthAtlas, a large scale multilingual dataset of 280,210 instances spanning 15 public health domains and 17 languages. We further propose a large language model (LLM) assisted construction and quality control pipeline with retrieval, deduplication, evidence grounding checks, and label validation to improve consistency at scale. Finally, we present a domain aligned evaluator distilled from high confidence judgments of diverse LLMs to assess outputs along six dimensions: Accuracy, Reasoning, Completeness, Consensus Alignment, Terminology Norms, and Insightfulness. Together, these contributions enable reproducible training and evaluation of LLMs for safety critical public health reasoning beyond conventional QA benchmarks. We publicly release project codebase, evaluator, and model at:: https://github.com/Jan8217/GlobalHealthAtlas, https://huggingface.co/aerovane0/GlobalHealthAtlas_Public_Evaluator and https://huggingface.co/aerovane0/GlobalHealthAtlas_Public_Model

LLM-as-a-judge has emerged as a cornerstone technique for evaluating large language models by leveraging LLM reasoning to score prompt-response pairs. Since LLM judgments are stochastic, practitioners commonly query each pair multiple times to estimate mean scores accurately. This raises a critical challenge: given a fixed computational budget B, how to optimally allocate queries across K prompt-response pairs to minimize estimation error? % We present a principled variance-adaptive approach leveraging multi-armed bandit theory and concentration inequalities. Our method dynamically allocates queries based on estimated score variances, concentrating resources where uncertainty is highest. Further, our algorithm is shown to achieve a worst-case score-estimation error of Oleft(frac{sum_{i=1^K σ_i^2}{B}}right), σ_i^2 being the unknown score variance for pair i in [K] with near-optimal budget allocation. % Experiments on Summarize-From-Feedback and HelpSteer2 demonstrate that our method significantly outperforms uniform allocation, reducing worst-case estimation error while maintaining identical budgets. Our work establishes a theoretical foundation for efficient LLM evaluation with practical implications for AI safety, model alignment, and automated assessment at scale.

Tool tracking in surgical videos is essential for advancing computer-assisted interventions, such as skill assessment, safety zone estimation, and human-machine collaboration. However, the lack of context-rich datasets limits AI applications in this field. Existing datasets rely on overly generic tracking formalizations that fail to capture surgical-specific dynamics, such as tools moving out of the camera's view or exiting the body. This results in less clinically relevant trajectories and a lack of flexibility for real-world surgical applications. Methods trained on these datasets often struggle with visual challenges such as smoke, reflection, and bleeding, further exposing the limitations of current approaches. We introduce CholecTrack20, a specialized dataset for multi-class, multi-tool tracking in surgical procedures. It redefines tracking formalization with three perspectives: (i) intraoperative, (ii) intracorporeal, and (iii) visibility, enabling adaptable and clinically meaningful tool trajectories. The dataset comprises 20 full-length surgical videos, annotated at 1 fps, yielding over 35K frames and 65K labeled tool instances. Annotations include spatial location, category, identity, operator, phase, and scene visual challenge. Benchmarking state-of-the-art methods on CholecTrack20 reveals significant performance gaps, with current approaches (< 45\% HOTA) failing to meet the accuracy required for clinical translation. These findings motivate the need for advanced and intuitive tracking algorithms and establish CholecTrack20 as a foundation for developing robust AI-driven surgical assistance systems.