RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing
By: Hao Xiang , Tianyi Tang , Yang Su and more
Potential Business Impact:
Tests how well AI can pretend to be people.
Recent advancements in Large Language Models (LLMs) have shown outstanding potential for role-playing applications. Evaluating these capabilities is becoming crucial yet remains challenging. Existing benchmarks mostly adopt a \textbf{character-centric} approach, simplify user-character interactions to isolated Q&A tasks, and fail to reflect real-world applications. To address this limitation, we introduce RMTBench, a comprehensive \textbf{user-centric} bilingual role-playing benchmark featuring 80 diverse characters and over 8,000 dialogue rounds. RMTBench includes custom characters with detailed backgrounds and abstract characters defined by simple traits, enabling evaluation across various user scenarios. Our benchmark constructs dialogues based on explicit user motivations rather than character descriptions, ensuring alignment with practical user applications. Furthermore, we construct an authentic multi-turn dialogue simulation mechanism. With carefully selected evaluation dimensions and LLM-based scoring, this mechanism captures the complex intention of conversations between the user and the character. By shifting focus from character background to user intention fulfillment, RMTBench bridges the gap between academic evaluation and practical deployment requirements, offering a more effective framework for assessing role-playing capabilities in LLMs. All code and datasets will be released soon.
Similar Papers
RoleRMBench & RoleRM: Towards Reward Modeling for Profile-Based Role Play in Dialogue Systems
Computation and Language
Makes AI better at pretending to be characters.
MTalk-Bench: Evaluating Speech-to-Speech Models in Multi-Turn Dialogues via Arena-style and Rubrics Protocols
Computation and Language
Tests how well computers understand talking.
MTBBench: A Multimodal Sequential Clinical Decision-Making Benchmark in Oncology
Machine Learning (CS)
Helps doctors make better cancer treatment choices.