Jiayu Tang, Guowei Peng, Qiuhao Xie, Yuning Yang, Xiurui Xie, Guisong Liu. OASIS: Mitigating Harmful Fine-tuning Attacks on LLMs via Orthogonal and Adaptive Safety Alignment Strategy. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 28407-28421, Association for Computational Linguistics, 2026. [doi]
Abstract is missing.