A Behavioral Trait Leaks into Preferences: Diagnosing Trait Interference in LLM User Simulators
PQA, a page-level quality anchoring method that guides simulators using a personalized anchor reflecting each user's intrinsic preference standard, is proposed, and experiments show PQA mitigates trait interference and improves the reliability of LLM-based simulator evaluation under activity shifts.
Chae-Ryung Kim, Sein Kim, Hongseok Kang et al.
· 0 citations