@article{ontheexploitabilityofreinforcement,
  title = {RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models},
  author = {Jiongxiao Wang and Junlin Wu and Muhao Chen and Yevgeniy Vorobeychik and Chaowei Xiao},
  year = {2023},
  eprint = {2311.09641},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.09641v2},
}