@inproceedings{belenki-etal-2025-optimizing,
    title = "Optimizing Pre-Training Data Mixtures with Mixtures of Data Expert Models",
    author = "Belenki, Lior  and
      Agarwal, Alekh  and
      Shi, Tianze  and
      Toutanova, Kristina",
    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/landing_page/2025.acl-long.1564/",
    pages = "32570--32587",
    ISBN = "979-8-89176-251-0"
}