publications

2026

1. ICML

   Dual Mechanisms of Value Expression: Intrinsic vs. Prompted Values in LLMs

   Jongwook Han^*, Jongwon Lim^*, Injin Kong, and Yohan Jo

   2026

   Accepted to ICML 2026

   arXiv
2. ACL

   Don’t Adapt Small Language Models for Tools; Adapt Tool Schemas to the Models

   Jonggeun Lee^*, Woojung Song^*, Jongwook Han, Haesung Pyun, and Yohan Jo

   2026

   Accepted to ACL 2026

   arXiv
3. EACL

   Quantifying Data Contamination in Psychometric Evaluations of LLMs

   Jongwook Han^*, Woojung Song^*, Jonggeun Lee^*, and Yohan Jo

   In Findings of the Association for Computational Linguistics: EACL 2026, 2026

   HTML

2025

1. ACL

   Value Portrait: Assessing Language Models’ Values through Psychometrically and Ecologically Valid Items

   Jongwook Han^*, Dongmin Choi^*, Woojung Song^*, Eun-Ju Lee, and Yohan Jo

   In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, 2025

   HTML PDF Video Poster
2. ACL

   PVP: An Image Dataset for Personalized Visual Persuasion with Persuasiveness Ratings, Persuasion Strategies, and Viewer Characteristics

   Junseo Kim, Jongwook Han, Dongmin Choi, Jongwook Yoon, Eun-Ju Lee, and Yohan Jo

   In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, 2025

   HTML PDF Poster
3. arXiv

   Human Psychometric Questionnaires Mischaracterize LLM Psychology: Evidence from Generation Behavior

   Woojung Song, Dongmin Choi, Yoonah Park, Jongwook Han, and Yohan Jo

   2025

   Under review

   arXiv
4. NeurIPS WS

   Dual Mechanisms of Value Expression: Decomposing Intrinsic and Prompted Values in Language Models

   Jongwook Han^*, Jongwon Lim^*, Injin Kong, and Yohan Jo

   In Mechanistic Interpretability Workshop at NeurIPS 2025, 2025

   Workshop paper

   HTML