一作ACL 2026Findings· Findings of ACL
Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLM s
Kai Wang · Haoyang You · Yang Zhang · Zhongjie Wang
摘要
A core challenge for faithful LLM role-playing is sustaining consistent characterization throughout long, open-ended dialogues, as models frequently fail to recall and accurately apply their designated persona knowledge without explicit cues. To tackle this, we propose the Memory-Driven Role-Play...