RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems

RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems Yihong Tang author Bo Wang author Xu Wang author Dongming Zhao author Jing Liu author Ruifang He author Yuexian Hou author 2025-01 text Proceedings of the 31st International Conference on Computational Linguistics Owen Rambow editor Leo Wanner editor Marianna Apidianaki editor Hend Al-Khalifa editor Barbara Di Eugenio editor Steven Schockaert editor Association for Computational Linguistics Abu Dhabi, UAE conference publication tang-etal-2025-rolebreak https://aclanthology.org/2025.coling-main.494/ 2025-01 7386 7402