Yu Ying Chiu

MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes

LitmusValues: Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas

Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models?

DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life

CulturalBench: a Robust, Diverse and Challenging Benchmark on Measuring (the Lack of) Cultural Knowledge of LLMs