Models and data from "Follow the Path: Reasoning over Knowledge Graph Paths to Improve Large Language Model Factuality".
Mike Zhang PRO
jjzha
AI & ML interests
Natural Language Processing, NLP Applications, NLP x HR, NLP x Education
Recent Activity
authored a paper 1 day ago
CommonLID: Re-evaluating State-of-the-Art Language Identification Performance on Web Data authored a paper 1 day ago
UniSkill: A Dataset for Matching University Curricula to Professional Competencies authored a paper 1 day ago
WorkRB: A Community-Driven Evaluation Framework for AI in the Work DomainOrganizations
Exams parsed from Dutch and Danish sources
Models for skill (span) extraction from, e.g., job ads in different languages
-
ESCOXLM-R: Multilingual Taxonomy-driven Pre-training for the Job Market Domain
Paper • 2305.12092 • Published • 1 -
jjzha/esco-xlm-roberta-large
Fill-Mask • 0.6B • Updated • 237 • 18 -
jjzha/escoxlmr_skill_extraction
Token Classification • 0.6B • Updated • 1.29k • 5 -
jjzha/escoxlmr_knowledge_extraction
Token Classification • 0.6B • Updated • 364 • 1
Models and data corresponding to the SEFL paper
-
SEFL: Harnessing Large Language Model Agents to Improve Educational Feedback Systems
Paper • 2502.12927 • Published • 1 -
jjzha/sefl
Viewer • Updated • 19.8k • 89 -
jjzha/Qwen2.5-0.5B-Instruct-SEFL
Text Generation • 0.5B • Updated • 6 • -
jjzha/Llama-3.2-1B-Instruct-SEFL
Text Generation • 1B • Updated • 2 •
Models for Skill Extraction from, e.g., job advertisements
-
SkillSpan: Hard and Soft Skill Extraction from English Job Postings
Paper • 2204.12811 • Published • 2 -
Kompetencer: Fine-grained Skill Classification in Danish Job Postings via Distant Supervision and Transfer Learning
Paper • 2205.01381 • Published -
jjzha/jobbert-base-cased
Fill-Mask • 0.1B • Updated • 9.67k • • 21 -
jjzha/jobberta-base
Fill-Mask • 0.1B • Updated • 89 • 13
Datasets annotated for skill (spans) in sentences, usually from job ads.
Models and data from "Follow the Path: Reasoning over Knowledge Graph Paths to Improve Large Language Model Factuality".
Models and data corresponding to the SEFL paper
-
SEFL: Harnessing Large Language Model Agents to Improve Educational Feedback Systems
Paper • 2502.12927 • Published • 1 -
jjzha/sefl
Viewer • Updated • 19.8k • 89 -
jjzha/Qwen2.5-0.5B-Instruct-SEFL
Text Generation • 0.5B • Updated • 6 • -
jjzha/Llama-3.2-1B-Instruct-SEFL
Text Generation • 1B • Updated • 2 •
Exams parsed from Dutch and Danish sources
Models for Skill Extraction from, e.g., job advertisements
-
SkillSpan: Hard and Soft Skill Extraction from English Job Postings
Paper • 2204.12811 • Published • 2 -
Kompetencer: Fine-grained Skill Classification in Danish Job Postings via Distant Supervision and Transfer Learning
Paper • 2205.01381 • Published -
jjzha/jobbert-base-cased
Fill-Mask • 0.1B • Updated • 9.67k • • 21 -
jjzha/jobberta-base
Fill-Mask • 0.1B • Updated • 89 • 13
Models for skill (span) extraction from, e.g., job ads in different languages
-
ESCOXLM-R: Multilingual Taxonomy-driven Pre-training for the Job Market Domain
Paper • 2305.12092 • Published • 1 -
jjzha/esco-xlm-roberta-large
Fill-Mask • 0.6B • Updated • 237 • 18 -
jjzha/escoxlmr_skill_extraction
Token Classification • 0.6B • Updated • 1.29k • 5 -
jjzha/escoxlmr_knowledge_extraction
Token Classification • 0.6B • Updated • 364 • 1
Datasets annotated for skill (spans) in sentences, usually from job ads.