@inproceedings{he-etal-2024-softdedup,
    title = "{S}oft{D}edup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training",
    author = "He, Nan  and
      Xiong, Weichen  and
      Liu, Hanwen  and
      Liao, Yi  and
      Ding, Lei  and
      Zhang, Kai  and
      Tang, Guohua  and
      Han, Xiao  and
      Wei, Yang",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.acl-long.220/",
    doi = "10.18653/v1/2024.acl-long.220",
    pages = "4011--4022"
}