Jing Yao

AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference

CAReDiO: Enhancing Cultural Alignment of LLM via Representativeness and Distinctiveness Guided Data Optimization

MMA-ASIA: A Multilingual and Multimodal Alignment Framework for Culturally Grounded Evaluation

Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models

Why Do You Answer Like That? Psychological Analysis on Underlying Connections between LLM's Values and Safety Risks

One Language, Many Gaps: Evaluating Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks

Elephant in the Room: Unveiling the Pitfalls of Human Proxies in Alignment