@inproceedings{wen-etal-2025-cheems,
    title = "Cheems: A Practical Guidance for Building and Evaluating {C}hinese Reward Models from Scratch",
    author = "Wen, Xueru  and
      Lou, Jie  and
      Li, Zichao  and
      Lu, Yaojie  and
      XingYu, XingYu  and
      Ji, Yuqiu  and
      Xu, Guohai  and
      Lin, Hongyu  and
      He, Ben  and
      Han, Xianpei  and
      Sun, Le  and
      Zhang, Debing",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.737/",
    pages = "15187--15211",
    ISBN = "979-8-89176-251-0",
    abstract = "Reward models (RMs) are crucial for aligning large language models (LLMs) with human preferences. However, most RM research is centered on English and relies heavily on synthetic resources, which leads to limited and less reliable datasets and benchmarks for Chinese. To address this gap, we introduce CheemsBench, a fully human-annotated RM evaluation benchmark within Chinese contexts, and CheemsPreference, a large-scale and diverse preference dataset annotated through human-machine collaboration to support Chinese RM training. We systematically evaluate open-source discriminative and generative RMs on CheemsBench and observe significant limitations in their ability to capture human preferences in Chinese scenarios. Additionally, based on CheemsPreference, we construct an RM that achieves state-of-the-art performance on CheemsBench, demonstrating the necessity of human supervision in RM training. Our findings reveal that scaled AI-generated data struggles to fully capture human preferences, emphasizing the importance of high-quality human supervision in RM development."
}