@inproceedings{zhao-etal-2025-codejudge,
    title = "{C}ode{J}udge-Eval: Can Large Language Models be Good Judges in Code Understanding?",
    author = "Zhao, Yuwei  and
      Luo, Ziyang  and
      Tian, Yuchen  and
      Lin, Hongzhan  and
      Yan, Weixiang  and
      Li, Annan  and
      Ma, Jing",
    editor = "Rambow, Owen  and
      Wanner, Leo  and
      Apidianaki, Marianna  and
      Al-Khalifa, Hend  and
      Eugenio, Barbara Di  and
      Schockaert, Steven",
    booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.coling-main.7/",
    pages = "73--95"
}