@article{saferlhfsafereinforcementlearningfrom,
  title = {Safe RLHF: Safe Reinforcement Learning from Human Feedback},
  author = {Josef Dai and Xuehai Pan and Ruiyang Sun and Jiaming Ji and Xinbo Xu and Mickel Liu and Yizhou Wang and Yaodong Yang},
  year = {2023},
  eprint = {2310.12773},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.12773v1},
}