@inproceedings{shi-etal-2025-dids,
    title = "{DIDS}: Domain Impact-aware Data Sampling for Large Language Model Training",
    author = "Shi, Weijie  and
      Zhang, Jipeng  and
      Wu, Yaguang  and
      Fang, Jingzhi  and
      Zhang, Shibo  and
      Zhao, Yao  and
      Chen, Hao  and
      Zhang, Ruiyuan  and
      Cui, Yue  and
      Zhu, Jia  and
      Han, Sirui  and
      Xu, Jiajie  and
      Zhou, Xiaofang",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.215/",
    pages = "4330--4350",
    ISBN = "979-8-89176-332-6"
}