@inproceedings{zhang-etal-2024-pacost,
    title = "{P}a{C}o{ST}: Paired Confidence Significance Testing for Benchmark Contamination Detection in Large Language Models",
    author = "Zhang, Huixuan  and
      Lin, Yun  and
      Wan, Xiaojun",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.findings-emnlp.97/",
    doi = "10.18653/v1/2024.findings-emnlp.97",
    pages = "1794--1809"
}