@inproceedings{yang-etal-2025-measuring,
    title = "Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric",
    author = "Yang, Yuming  and
      Nan, Yang  and
      Ye, Junjie  and
      Dou, Shihan  and
      Wang, Xiao  and
      Li, Shuo  and
      Lv, Huijie  and
      Gui, Tao  and
      Zhang, Qi  and
      Huang, Xuanjing",
    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.908/",
    pages = "18530--18549",
    ISBN = "979-8-89176-251-0"
}