@inproceedings{kwak-kim-2026-gap,
    title = "Gap-K{\%}: Measuring Top-1 Prediction Gap for Detecting Pretraining Data",
    author = "Kwak, Minseo  and
      Kim, Jaehyung",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1072/",
    pages = "23391--23405",
    ISBN = "979-8-89176-390-6",
    abstract = "The opacity of massive pretraining corpora in Large Language Models (LLMs) raises significant privacy and copyright concerns, making pretraining data detection a critical challenge.Existing state-of-the-art methods typically rely on token likelihoods, yet they often overlook the gap between the target token and the model{'}s top-1 prediction, as well as local correlations between adjacent tokens.In this work, we propose Gap-K{\%}, a novel pretraining data detection method grounded in the optimization dynamics of LLM pretraining. By analyzing the next-token prediction objective, we observe that discrepancies between the model{'}s top-1 prediction and the target token induce strong gradient signals, which are explicitly penalized during training.Motivated by this, Gap-K{\%} leverages the log probability gap between the top-1 predicted token and the target token, incorporating a sliding window strategy to capture local correlations and mitigate token-level fluctuations. Extensive experiments on the WikiMIA and MIMIR benchmarks demonstrate that Gap-K{\%} achieves state-of-the-art performance, consistently outperforming prior baselines across various model sizes and input lengths."
}