@inproceedings{zhao-etal-2025-coreeval,
    title = "{C}ore{E}val: Automatically Building Contamination-Resilient Datasets with Real-World Knowledge toward Reliable {LLM} Evaluation",
    author = "Zhao, Jingqian  and
      Wang, Bingbing  and
      Tu, Geng  and
      Zhang, Yice  and
      Wang, Qianlong  and
      Liang, Bin  and
      Li, Jing  and
      Xu, Ruifeng",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.1085/",
    pages = "22284--22306",
    ISBN = "979-8-89176-251-0",
    abstract = "Data contamination poses a significant challenge to the fairness of LLM evaluations in natural language processing tasks by inadvertently exposing models to test data during training.Current studies mitigate this issue by modifying existing datasets or generating new ones from freshly collected information. However, these methods fall short of ensuring contamination-resilient evaluation, as they fail to fully eliminate pre-existing knowledge from models or preserve the semantic complexity of the original datasets. To address these limitations, we propose $\textbf{CoreEval}$, a $\textbf{Co}$ntamination-$\textbf{re}$silient $\textbf{Eval}$uation strategy for automatically updating data with real-world knowledge. This approach begins by extracting entity relationships from the original data and leveraging the GDELT database to retrieve relevant and up-to-date knowledge. The retrieved knowledge is then recontextualized and integrated with the original data, which is refined and restructured to ensure semantic coherence and enhanced task relevance. Ultimately, a robust data reflection mechanism in a Chain-of-Thought manner to iteratively verify and refine labels, ensuring consistency between the updated and original datasets. Extensive experiments on updated datasets validate the robustness of CoreEval, demonstrating its effectiveness in mitigating performance overestimation caused by data contamination."
}