Toward Robust Personalized Alignment for LLMs: Mitigating Persona Drift in Multi-Turn Dialogue
This work proposes CORE, which separates turn-local evidence from persistent persona-state revision and selectively updates grounded user preferences through uncertainty-aware belief revision, and introduces PERSIST, a held-out post-anchor benchmark for persona-state robustness under sequential interaction stress.
Youyuan Zhang, Si-Yuan Li, Fang-Ming Liu et al.
· 1 citation