@inproceedings{zhang-etal-2026-huggingbrew,
    title = "{H}ugging{B}rew: Brewing High-Quality Mid-Training Data from the {H}ugging{F}ace Community Datasets",
    author = "Zhang, Han  and
      Chen, Ningqi  and
      Liu, Xiao  and
      Lin, Zhenghao  and
      Gong, Yeyun  and
      Lu, Yan  and
      Yang, Hanfang",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.1519/",
    pages = "32346--32365",
    ISBN = "979-8-89176-462-0"
}