@article{safealignersafetyalignmentagainst, title = {SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance}, author = {Caishuang Huang and Wanxu Zhao and Rui Zheng and Huijie Lv and WenYu Zhan and Shihan Dou and Sixian Li and Xiao Wang and Enyu Zhou and Junjie Ye and Yuming Yang and Tao Gui and Qi Zhang and Xuanjing Huang}, year = {2024}, eprint = {2406.18118}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.18118v4}, }