@inproceedings{huang-etal-2025-empirical,
    title = "An Empirical Study of {LLM}-as-a-Judge for {LLM} Evaluation: Fine-tuned Judge Model is not a General Substitute for {GPT}-4",
    author = "Huang, Hui  and
      Bu, Xingyuan  and
      Zhou, Hongli  and
      Qu, Yingqi  and
      Liu, Jing  and
      Yang, Muyun  and
      Xu, Bing  and
      Zhao, Tiejun",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/mtsummit-25-ingestion/2025.findings-acl.306/",
    doi = "10.18653/v1/2025.findings-acl.306",
    pages = "5880--5895",
    ISBN = "979-8-89176-256-5"
}