@inproceedings{zhou-etal-2024-emulated, title = "Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!", author = "Zhou, Zhanhui and Liu, Jie and Dong, Zhichen and Liu, Jiaheng and Yang, Chao and Ouyang, Wanli and Qiao, Yu", editor = "Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek", booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", month = aug, year = "2024", address = "Bangkok, Thailand", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2024.acl-long.842/", doi = "10.18653/v1/2024.acl-long.842", pages = "15810--15830" }