Qin Liu 0010, Chao Shang, Ling Liu, Nikolaos Pappas 0004, Jie Ma 0005, Neha Anna John, Srikanth Doss, Lluís Màrquez, Miguel Ballesteros, Yassine Benajiba. Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models. In Wanxiang Che, Joyce Nabende, Ekaterina Shutova, Mohammad Taher Pilehvar, editors, Findings of the Association for Computational Linguistics, ACL 2025, Vienna, Austria, July 27 - August 1, 2025. pages 3631-3643, Association for Computational Linguistics, 2025. [doi]
Abstract is missing.