Can Large Language Models Explain Themselves?
Paper • 2401.07927 • Published • 5
Alexsio nau
alexsio274
AI & ML interests
None yet
Recent Activity
upvoted a paper 4 days ago
Can Large Language Models Explain Themselves? upvoted a paper 4 days ago
Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency upvoted a paper 4 days ago
SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?Organizations
upvoted 20
papers 4 days ago
Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency
Paper • 2601.05905 • Published • 21
SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?
Paper • 2505.20295 • Published • 1
Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models
Paper • 2602.04649 • Published • 13
Self-consistency for open-ended generations
Paper • 2307.06857 • Published • 12
Soft Self-Consistency Improves Language Model Agents
Paper • 2402.13212 • Published • 2
Nuance Matters: Probing Epistemic Consistency in Causal Reasoning
Paper • 2409.00103 • Published • 1
Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring
Paper • 2502.05242 • Published • 1
Thinking with Many Minds: Using Large Language Models for Multi-Perspective Problem-Solving
Paper • 2501.02348 • Published • 1
Reasoning with Confidence: Efficient Verification of LLM Reasoning Steps via Uncertainty Heads
Paper • 2511.06209 • Published • 20
Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives
Paper • 2401.02009 • Published • 2
The Trickle-down Impact of Reward (In-)consistency on RLHF
Paper • 2309.16155 • Published • 2
MyGO Multiplex CoT: A Method for Self-Reflection in Large Language Models via Double Chain of Thought Thinking
Paper • 2501.13117 • Published • 1
The Consciousness Prior
Paper • 1709.08568 • Published • 1
Are We on the Right Way to Assessing LLM-as-a-Judge?
Paper • 2512.16041 • Published • 35
Toward Adaptive Reasoning in Large Language Models with Thought Rollback
Paper • 2412.19707 • Published • 1
Improved Techniques for Training Consistency Models
Paper • 2310.14189 • Published • 1
Are LLMs classical or nonmonotonic reasoners? Lessons from generics
Paper • 2406.06590 • Published • 1
Stable Consistency Tuning: Understanding and Improving Consistency Models
Paper • 2410.18958 • Published • 11
Metacognitive Prompting Improves Understanding in Large Language Models
Paper • 2308.05342 • Published • 3