@inproceedings{bai-etal-2025-efficient-pretraining,
    title = "Efficient Pretraining Data Selection for Language Models via Multi-Actor Collaboration",
    author = "Bai, Tianyi  and
      Yang, Ling  and
      Wong, Zhen Hao  and
      Sun, Fupeng  and
      Zhuang, Xinlin  and
      Peng, Jiahui  and
      Zhang, Chi  and
      Wu, Lijun  and
      Jiantao, Qiu  and
      Zhang, Wentao  and
      Yuan, Binhang  and
      He, Conghui",
    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.466/",
    pages = "9465--9491",
    ISBN = "979-8-89176-251-0"
}