Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs
Weixiang Zhao, Yulin Hu, Yang Deng, Jiahe Guo, Xingyu Sui, Xinyang Han, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
Authors
- Yanyan Zhao (ORCID: https://orcid.org/0000-0002-1828-5038)
- Yang Deng (ORCID: https://orcid.org/0000-0002-8122-5943)
- Yulin Hu (ORCID: https://orcid.org/0000-0002-1047-9436)
- Jiahe Guo (ORCID: https://orcid.org/0009-0008-8828-8155)
- Xin Sui (ORCID: https://orcid.org/0000-0002-6830-7012)
- Tat‐Seng Chua (ORCID: https://orcid.org/0000-0001-6097-7807)
- An Zhang (ORCID: https://orcid.org/0000-0002-9338-6250)
- Xinyang Han
- Ting Liu (ORCID: https://orcid.org/0009-0000-4298-1896)
- Weixiang Zhao
- Bing Qin (ORCID: https://orcid.org/0009-0001-1429-3348)
Publication Details
- Published
- 2025-01-01
- DOI
- https://doi.org/10.18653/v1/2025.acl-long.544
- Primary Topic
- Ethics and Social Impacts of AI
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Ministry of Education, India
- National Science and Technology Major Project
- Fundamental Research Funds for the Central Universities