2 papers
cs.CL2026
Generative Personality Simulation via Theory-Informed Structured Interview
Pengda Wang, Huiqi Zou, Han Jiang +5
Despite their potential as human proxies, LLMs often fail to generate heterogeneous data with human-like diversity, thereby diminishing their value in advancing social science rese…
cs.HC2025
Can LLM "Self-report"?: Evaluating the Validity of Self-report Scales in Measuring Personality Design in LLM-based Chatbots
Huiqi Zou, Pengda Wang, Zihan Yan +2
A chatbot's personality design is key to interaction quality. As chatbots evolved from rule-based systems to those powered by large language models (LLMs), evaluating the effective…