@inproceedings{tang-etal-2025-rise,
    title = "The Rise of Darkness: Safety-Utility Trade-Offs in Role-Playing Dialogue Agents",
    author = "Tang, Yihong  and
      Chen, Kehai  and
      Bai, Xuefeng  and
      Niu, Zheng-Yu  and
      Wang, Bo  and
      Liu, Jie  and
      Zhang, Min",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.findings-acl.839/",
    pages = "16313--16337",
    ISBN = "979-8-89176-256-5",
    abstract = "Large Language Models (LLMs) have made remarkable advances in role-playing dialogue agents, demonstrating their utility in character simulations. However, it remains challenging for these agents to balance character portrayal utility with content safety because this essential character simulation often comes with the risk of generating unsafe content. To address this issue, we first conduct a systematic exploration of the safety-utility trade-off across multiple LLMs. Our analysis reveals that risk scenarios created by villain characters and user queries (referred to as risk coupling) contribute to this trade-off. Building on this, we propose a novel Adaptive Dynamic Multi-Preference (ADMP) method, which dynamically adjusts safety-utility preferences based on the degree of risk coupling and guides the model to generate responses biased toward utility or safety. We further introduce Coupling Margin Sampling (CMS) into coupling detection to enhance the model{'}s ability to handle high-risk scenarios. Experimental results demonstrate that our approach improves safety metrics while maintaining utility."
}