@inproceedings{zhu-etal-2024-inference,
    title = "Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation",
    author = "Zhu, Qin  and
      Cheng, Qinyuan  and
      Peng, Runyu  and
      Li, Xiaonan  and
      Peng, Ru  and
      Liu, Tengxiao  and
      Qiu, Xipeng  and
      Huang, Xuanjing",
    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/ingest_wac_2008/2024.findings-emnlp.532/",
    doi = "10.18653/v1/2024.findings-emnlp.532",
    pages = "9113--9129"
}