Ziang Xiao

PICACO: Pluralistic In-Context Value Alignment via Total Correlation Optimization

TALES: Text Adventure Learning Environment Suite

Can LLM "Self-report"?: Evaluating the Validity of Self-report Scales in Measuring Personality Design in LLM-based Chatbots

Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing

From Queries to Criteria: Understanding How Astronomers Evaluate LLMs