@article{canrlhfbemoreefficientwithimperfect,
  title = {Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective},
  author = {Jiawei Huang and Bingcong Li and Christoph Dann and Niao He},
  year = {2025},
  eprint = {2502.19255},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.19255v3},
}