@inproceedings{yu-etal-2025-craw4llm,
    title = "{C}raw4{LLM}: Efficient Web Crawling for {LLM} Pretraining",
    author = "Yu, Shi  and
      Liu, Zhiyuan  and
      Xiong, Chenyan",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-acl.712/",
    pages = "13843--13851",
    ISBN = "979-8-89176-256-5"
}