@article{mitigatingrewardhackingviainformation,
  title = {InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling},
  author = {Yuchun Miao and Sen Zhang and Liang Ding and Rong Bao and Lefei Zhang and DaCheng Tao},
  year = {2024},
  eprint = {2402.09345},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.09345v5},
}