Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMs
Year: 2026
Type: conference-paper
Abstract: A core challenge for faithful LLM roleplaying 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-Playing paradigm.Inspired by Stanislavski's "emotional memory" acting theory, this paradigm frames persona knowledge as the LLM's internal memory store, requiring retrieval and application based solely on dialogue context, thereby providing a rigorous test of depth and autonomous use of knowledge.Centered on this paradigm, we contribute: (1) MREval, a fine-grained evaluation framework assessing four memory-driven abilities-Anchoring, Selecting, Bounding, and Enacting; (2) MR-Prompt, a prompting architecture that guides structured memory retrieval and response generation; and (3) MRBench, a bilingual (Chinese/English) benchmark for fine-grained diagnosis.The novel paradigm provides a comprehensive diagnostic for four-stage role-playing abilities across 12 LLMs.Crucially, experiments show that MRPrompt allows small models (e.g., Qwen3-8B) to match the performance of much larger closed-source LLMs (e.g., Qwen3-Max and GLM-4.7), and confirm that upstream memory gains directly enhance downstream response quality, validating the staged theoretical foundation.
Authors: Kai Wang, Haoyang You, Yang Zhang, Zhongjie Wang
Institutions: Harbin Institute of Technology, Macquarie University
Language: English
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166852164