@article{emulateddisalignmentsafetyalignmentfor,
  title = {Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!},
  author = {Zhanhui Zhou and Jie Liu and Zhichen Dong and Jiaheng Liu and Chao Yang and Wanli Ouyang and Yu Qiao},
  year = {2024},
  eprint = {2402.12343},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.12343v4},
}