Integrated M.S.-Ph.D. in Data Science, Seoul National University
I believe agents can already solve many of the problems we face in the real world. Still, people want better agents, and I don't think we get there just by making models code or complete tasks more accurately. We get there by understanding how agents actually behave, and what values they carry while doing so. My research covers these two sides: Agents and Value Alignment.
I'm currently looking for a summer internship where I can contribute to research on agents or value alignment. I'm also always open to collaboration. Reach me at opusdeisong@snu.ac.kr.
EMNLP 2026 Paper accepted to the main conference
ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?
EMNLP 2026 Paper accepted to the main conference
Human Psychometric Questionnaires Mischaracterize LLM Behavior
Scholarship Presidential Science Scholarship for Graduate Students
Ministry of Science and ICT · 2026 – 2027
ACL 2026 Paper accepted to the main conference
Don't Adapt Small Language Models for Tools; Adapt Tool Schemas to the Models
TACL Paper accepted for publication
Psychometric Item Validation Using Virtual Respondents with Trait-Response Mediators
EACL 2026 Paper accepted to Findings
Quantifying Data Contamination in Psychometric Evaluations of LLMs
ICLR 2026 Paper accepted
ACL 2025 Paper accepted to the main conference