Yu Ying Chiu

DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life
WildHallucinations: Evaluating Long-form Factuality in LLMs with Real-World Entity Queries
CulturalBench: a Robust, Diverse and Challenging Benchmark on Measuring the (Lack of) Cultural Knowledge of LLMs

Published with Wowchemy — the free, open source website builder that empowers creators.