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

arXiv: https://arxiv.org/abs/2411.03823 · HTML: https://mlsanity.com/paper/2411.03823/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 16 of its 31 references that are in the map.
- First posted on arXiv 6 Nov 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [nocaps: novel object captioning at scale](https://mlsanity.com/paper/1812.08658/) (2018)
- [OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents](https://mlsanity.com/paper/2306.16527/) (2023)
- [Investigating Data Contamination in Modern Benchmarks for Large Language Models](https://mlsanity.com/paper/2311.09783/) (2023)
- [MileBench: Benchmarking MLLMs in Long Context](https://mlsanity.com/paper/2404.18532/) (2024)

## Built on by (most cited first, 10 of 10)

- [KBE-DME: Dynamic Multimodal Evaluation via Knowledge Enhanced Benchmark Evolution](https://mlsanity.com/paper/2510.21182/) (2025)
- [FiMMIA: scaling semantic perturbation-based membership inference across modalities](https://mlsanity.com/paper/2512.02786/) (2025)
- [Can MLLMs Read Students' Minds? Unpacking Multimodal Error Analysis in Handwritten Math](https://mlsanity.com/paper/2603.24961/) (2026)
- [Benchmark Shadows: Data Alignment, Parameter Footprints, and Generalization in Large Language Models](https://mlsanity.com/paper/2604.07363/) (2026)
- [VGenST-Bench: A Benchmark for Spatio-Temporal Reasoning via Active Video Synthesis](https://mlsanity.com/paper/2605.22570/) (2026)
- [A Controlled Audit of Pretraining Contamination in Public Medical Vision-Language Benchmarks](https://mlsanity.com/paper/2606.10066/) (2026)
- [REKEY: Metadata-Grounded Visual-Key Regeneration for Contamination-Resilient VQA Evaluation](https://mlsanity.com/paper/2606.20736/) (2026)
- [MMBench-Live: A Continuously Evolving Benchmark for Multimodal Models](https://mlsanity.com/paper/2607.01813/) (2026)
- [Learning to Zoom Efficiently with a Contrastive Curriculum](https://mlsanity.com/paper/2609.03206/) (2026)
- [Auditing VLM Benchmarks from Existing Evaluation Runs](https://mlsanity.com/paper/2610.13548/) (2026)

## Abstract (arXiv)

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.