@inproceedings{zhao-etal-2026-ultrax,
    title = "{U}ltra{X}: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing",
    author = "Zhao, Xinlong  and
      Liu, Dongsheng  and
      Zhao, Hengyu  and
      Fu, Zixuan  and
      Wang, Zheng  and
      Cai, Jie  and
      Zhou, Jie  and
      Ma, Qiang  and
      Zhou, Xuanhe  and
      Han, Xu  and
      Wang, Yudong  and
      Liu, Zhiyuan",
    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.1132/",
    pages = "25915--25952",
    ISBN = "979-8-89176-459-0"
}