@inproceedings{zhao-etal-2025-beware,
    title = "Beware of Your Po! Measuring and Mitigating {AI} Safety Risks in Role-Play Fine-Tuning of {LLM}s",
    author = "Zhao, Weixiang  and
      Hu, Yulin  and
      Deng, Yang  and
      Guo, Jiahe  and
      Sui, Xingyu  and
      Han, Xinyang  and
      Zhang, An  and
      Zhao, Yanyan  and
      Qin, Bing  and
      Chua, Tat-Seng  and
      Liu, Ting",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.544/",
    pages = "11112--11137",
    ISBN = "979-8-89176-251-0",
    abstract = "Role-playing enables large language models (LLMs) to engage users in immersive and personalized interactions, but it also introduces significant safety risks. Existing role-play fine-tuning techniques improve role adaptability but may degrade safety performance, particularly for villainous characters. In this work, we conduct the first comprehensive assessment of role-play fine-tuning risks by training 95 role-specific LLMs using RoleBench. Our experiments reveal that role-play fine-tuning leads to a noticeable decline in safety performance, with safety risks varying based on character traits. To tackle this challenge, we propose Safety-Aware Role-Play Fine-Tuning (SaRFT), a novel method designed to balance role-playing capabilities and safety. Extensive experiments on LLaMA-3-8B-Instruct, Gemma-2-9B-it, and Qwen2.5-7B-Instruct demonstrate that SaRFT consistently outperforms state-of-the-art baselines under both LoRA and full-parameter fine-tuning settings. Our findings highlight the necessity of role-adaptive safety measures and provide insights into mitigating role-specific safety risks in role-playing LLMs."
}