@inproceedings{song-etal-2025-text,
    title = "Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal {LLM}",
    author = "Song, Dingjie  and
      Lai, Sicheng  and
      Wang, Mingxuan  and
      Chen, Shunian  and
      Sun, Lichao  and
      Wang, Benyou",
    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.556/",
    doi = "10.18653/v1/2025.findings-emnlp.556",
    pages = "10527--10542",
    ISBN = "979-8-89176-335-7",
    abstract = "The rapid advancement of multimodal large language models (MLLMs) has significantly enhanced performance across benchmarks. However, data contamination {---} partial/entire benchmark data is included in the model{'}s training set {---} poses critical challenges for fair evaluation. Existing detection methods for unimodal large language models (LLMs) are inadequate for MLLMs due to multimodal data complexity and multi-phase training. We systematically analyze multimodal data contamination using our analytical framework, MM-DETECT, which defines two contamination categories {---} unimodal and cross-modal {---} and effectively quantifies contamination severity across multiple-choice and caption-based Visual Question Answering tasks. Evaluations on twelve MLLMs and five benchmarks reveal significant contamination, particularly in proprietary models and older benchmarks. Crucially, contamination sometimes originates during unimodal pre-training rather than solely from multimodal fine-tuning. Our insights refine contamination understanding, guiding evaluation practices and improving multimodal model reliability."
}