@inproceedings{kim-etal-2025-rethinking-kenlm,
    title = "Rethinking {K}en{LM}: Good and Bad Model Ensembles for Efficient Text Quality Filtering in Large Web Corpora",
    author = "Kim, Yungi  and
      Ha, Hyunsoo  and
      Lee, Sukyung  and
      Kim, Jihoo  and
      Yang, Seonghoon  and
      Park, Chanjun",
    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 2: Short Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.acl-short.4/",
    pages = "53--58",
    ISBN = "979-8-89176-252-7"
}