MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning PermalinkCOLM, 2026Ayoung Lee, Ryan Kwon, Yunxiang Zhang, Yuxuan Liu, Peter Railton, Lu Wang Paper | Dataset | Model
CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives PermalinkICLR, 2026Ayoung Lee, Ryan Sungmo Kwon, Peter Railton, Lu Wang Paper | Code | Dataset
Representation Bending for Large Language Model Safety PermalinkACL, 2025Ashkan Yousefpour*, Taeheon Kim*, Ryan S. Kwon, Seungbeen Lee, Wonje Jeung, Seungju Han, Alvin Wan, Harrison Ngan, Youngjae Yu, Jonghyun Choi Paper | Code | Model
