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

Source: [Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLM](<https://www.sota2.com/research/paper/68fa7b741e209131cea88968>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:41:29.127Z

Authors: Dingjie Song, Sicheng Lai, Mingxuan Wang, Shunian Chen, Lichao Sun, Benyou Wang

Published: 2024-11-06T10:44:15.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2411.03823>)

[PDF](<https://arxiv.org/pdf/2411.03823.pdf>)
