@inproceedings{hidayat-etal-2025-simulating,
    title = "Simulating Training Data Leakage in Multiple-Choice Benchmarks for {LLM} Evaluation",
    author = "Hidayat, Naila Shafirni  and
      Al Kautsar, Muhammad Dehan  and
      Wicaksono, Alfan Farizki  and
      Koto, Fajri",
    editor = "Akter, Mousumi  and
      Chowdhury, Tahiya  and
      Eger, Steffen  and
      Leiter, Christoph  and
      Opitz, Juri  and
      {\c{C}}ano, Erion",
    booktitle = "Proceedings of the 5th Workshop on Evaluation and Comparison of NLP Systems",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.eval4nlp-1.3/",
    pages = "21--39",
    ISBN = "979-8-89176-305-0",
    abstract = "The performance of large language models (LLMs) continues to improve, as reflected in rising scores on standard benchmarks. However, the lack of transparency around training data raises concerns about potential overlap with evaluation sets and the fairness of reported results. Although prior work has proposed methods for detecting data leakage, these approaches primarily focus on identifying outliers and have not been evaluated under controlled simulated leakage conditions. In this work, we compare existing leakage detection techniques, namely permutation and n-gram-based methods, under a continual pretraining setup that simulates real-world leakage scenarios, and additionally explore a lightweight method we call semi-half question. We further introduce two efficient extensions, permutation-R and permutation-Q. While semi-half offers a low-cost alternative, our analysis shows that the n-gram method consistently achieves the highest F1-Score, performing competitively with permutation-Q. We also refine these techniques to support instance-level detection and reduce computational overhead. Leveraging the best-performing method, we create cleaned versions of MMLU and HellaSwag, and re-evaluate several LLMs. Our findings present a practical path toward more reliable and transparent evaluations, and we recommend contamination checks as a standard practice before releasing benchmark results."
}