@inproceedings{chen-etal-2024-accuracy,
    title = "The Accuracy Paradox in {RLHF}: When Better Reward Models Don`t Yield Better Language Models",
    author = "Chen, Yanjun  and
      Zhu, Dawei  and
      Sun, Yirong  and
      Chen, Xinghao  and
      Zhang, Wei  and
      Shen, Xiaoyu",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.emnlp-main.174/",
    doi = "10.18653/v1/2024.emnlp-main.174",
    pages = "2980--2989"
}