@article{theaccuracyparadoxinrlhfwhenbetter,
  title = {The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models},
  author = {Yanjun Chen and Dawei Zhu and Yirong Sun and Xinghao Chen and Wei zhang and Xiaoyu Shen},
  year = {2024},
  eprint = {2410.06554},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.06554v2},
}