@inproceedings{xiang-etal-2025-rmtbench,
    title = "{RMTB}ench: Benchmarking {LLM}s Through Multi-Turn User-Centric Role-Playing",
    author = "Xiang, Hao  and
      Tang, Tianyi  and
      Su, Yang  and
      Yu, Bowen  and
      Yang, An  and
      Huang, Fei  and
      Zhang, Yichang  and
      Lu, Yaojie  and
      Lin, Hongyu  and
      Han, Xianpei  and
      Zhou, Jingren  and
      Lin, Junyang  and
      Sun, Le",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.730/",
    doi = "10.18653/v1/2025.findings-emnlp.730",
    pages = "13555--13571",
    ISBN = "979-8-89176-335-7",
    abstract = "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."
}