@article{iterativedatasmoothingmitigatingreward,
  title = {Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF},
  author = {Banghua Zhu and Michael I. Jordan and Jiantao Jiao},
  year = {2024},
  eprint = {2401.16335},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2401.16335v1},
}