@inproceedings{zhang-etal-2026-auditing,
    title = "Auditing {C}hinese Web-scale Corpora via Sampled {BPE} Token Statistics",
    author = "Zhang, Qingjie  and
      Tang, Ziqi  and
      Zhang, Jie  and
      Deng, Gelei  and
      Li, Jinfeng  and
      Chen, YueFeng  and
      Yang, Yitong  and
      Xue, Hui  and
      Zhang, Tianwei  and
      Qiu, Han",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.1331/",
    pages = "30352--30379",
    ISBN = "979-8-89176-459-0"
}