@inproceedings{kaneko-baldwin-2025-investigating,
    title = "Investigating How Pre-training Data Leakage Affects Models' Reproduction and Detection Capabilities",
    author = "Kaneko, Masahiro  and
      Baldwin, Timothy",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1201/",
    pages = "23556--23566",
    ISBN = "979-8-89176-332-6"
}