@inproceedings{hou-etal-2025-lne,
    title = "{LNE}-Blocking: An Efficient Framework for Contamination Mitigation Evaluation on Large Language Models",
    author = "Hou, Ruijie  and
      Jiao, Yueyang  and
      Hu, Hanxu  and
      Li, Yingming  and
      Lam, Wai  and
      Zhang, Huajian  and
      Lu, Hongyuan",
    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://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.188/",
    doi = "10.18653/v1/2025.findings-emnlp.188",
    pages = "3512--3528",
    ISBN = "979-8-89176-335-7",
    abstract = "The problem of data contamination is now almost inevitable during the development of large language models (LLMs), with the training data commonly integrating those evaluation benchmarks even unintentionally. This problem subsequently makes it hard to benchmark LLMs fairly. Instead of constructing contamination-free datasets (quite hard), we propose a novel framework, \textbf{LNE-Blocking}, to restore model performance prior to contamination on potentially leaked datasets. Our framework consists of two components: contamination detection and disruption operation. For the prompt, the framework first uses the contamination detection method, \textbf{LNE}, to assess the extent of contamination in the model. Based on this, it adjusts the intensity of the disruption operation, \textbf{Blocking}, to elicit non-memorized responses from the model. Our framework is the first to efficiently restore the model{'}s greedy decoding performance. This comes with a strong performance on multiple datasets with potential leakage risks, and it consistently achieves stable recovery results across different models and varying levels of data contamination. We release the code at \url{https://github.com/RuijieH/LNE-Blocking} to facilitate research."
}