@inproceedings{liu-etal-2025-empirical,
    title = "Empirical Study on Data Attributes Insufficiency of Evaluation Benchmarks for {LLM}s",
    author = "Liu, Chuang  and
      Jin, Renren  and
      Yao, Zheng  and
      Li, Tianyi  and
      Cheng, Liang  and
      Steedman, Mark  and
      Xiong, Deyi",
    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.403/",
    pages = "6024--6038"
}