@inproceedings{yeen-etal-2025-manta,
    title = "{MANTA}: A Scalable Pipeline for Transmuting Massive Web Corpora into Instruction Datasets",
    author = "Yeen, Heuiyeen  and
      Hong, Seokhee  and
      Yun, Hyeongu  and
      Lee, Jinsik",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-emnlp.1019/",
    pages = "18755--18770",
    ISBN = "979-8-89176-335-7"
}