@article{informationtheoreticrewardmodelingforsta,
  title = {Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking},
  author = {Yuchun Miao and Liang Ding and Sen Zhang and Rong Bao and Lefei Zhang and Dacheng Tao},
  year = {2025},
  eprint = {2510.13694},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.13694},
}