@article{oneshotsafetyalignmentforlargelanguage,
  title = {One-Shot Safety Alignment for Large Language Models via Optimal Dualization},
  author = {Xinmeng Huang and Shuo Li and Edgar Dobriban and Osbert Bastani and Hamed Hassani and Dongsheng Ding},
  year = {2024},
  eprint = {2405.19544},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.19544v3},
}