Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLM

ACL ARR 2025 May Submission1272 Authors

Abstract: The rapid advancement of multimodal large language models (MLLMs) has significantly enhanced performance across benchmarks. However, data contamination — unintentional memorization of benchmark data during model training — 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.

Paper Type: Long

Research Area: Ethics, Bias, and Fairness

Research Area Keywords: data ethics, model bias/fairness evaluation, model bias/unfairness mitigation, transparency

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Publicly available software and/or pre-trained models, Data analysis

Languages Studied: English

Submission Number: 1272