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

• URL: http://arxiv.org/abs/2411.03823v3
• Date: Sat, 20 Sep 2025 19:01:48 GMT
• Title: Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLM
• Authors: Dingjie Song, Sicheng Lai, Mingxuan Wang, Shunian Chen, Lichao Sun, Benyou Wang,
• Abstract summary: multimodal large language models (MLLMs) have significantly enhanced performance across benchmarks.<n>Existing detection methods for unimodal large language models (LLMs) are inadequate for MLLMs due to multimodal data complexity and multi-phase training.<n>We analyze multimodal data contamination using our analytical framework, MM-Detect, which defines two contamination categories-unimodal and cross-modal.
• Score: 53.05486269607166
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• PENDULUM: A Benchmark for Assessing Sycophancy in Multimodal Large Language Models [43.767942065379366]
  Sycophancy is a tendency of AI models to agree with user input at the expense of factual accuracy or in contradiction of visual evidence.<n>We introduce a comprehensive evaluation benchmark, textitPENDULUM, comprising approximately 2,000 human-curated Visual Question Answering pairs.<n>We observe substantial variability in model robustness and a pronounced susceptibility to sycophantic and hallucinatory behavior.
  arXiv  Detail & Related papers  (2025-12-22T12:49:12Z)
• Contamination Detection for VLMs using Multi-Modal Semantic Perturbation [73.76465227729818]
  Open-source Vision-Language Models (VLMs) have achieved state-of-the-art performance on benchmark tasks.<n>Pretraining corpora raise a critical concern for both practitioners and users: inflated performance due to test-set leakage.<n>We show that existing detection approaches either fail outright or exhibit inconsistent behavior.<n>We propose a novel simple yet effective detection method based on multi-modal semantic perturbation.
  arXiv  Detail & Related papers  (2025-11-05T18:59:52Z)
• Advancing Multimodal Reasoning Capabilities of Multimodal Large Language Models via Visual Perception Reward [87.06604760273372]
  We propose Perception-R1, which introduces a novel visual perception reward that explicitly encourages MLLMs to perceive the visual content accurately.<n>We show that Perception-R1 achieves state-of-the-art performance on most benchmarks using only 1,442 training data.
  arXiv  Detail & Related papers  (2025-06-08T16:48:42Z)
• Reasoning Multimodal Large Language Model: Data Contamination and Dynamic Evaluation [9.434966074326056]
  Multimodal Large Language Models (MLLMs) show impressive vision-language benchmark performance, yet growing concerns about data contamination risk masking true generalization.<n>We propose a novel dynamic evaluation framework to rigorously assess MLLM generalization, moving beyond static benchmarks.<n>We demonstrate that fine-tuning on simulated test data (extreme contamination) drastically sharpens task-specific performance but harms overall generalization.
  arXiv  Detail & Related papers  (2025-06-08T15:52:38Z)
• Truth in the Few: High-Value Data Selection for Efficient Multi-Modal Reasoning [71.3533541927459]
  We propose a novel data selection paradigm termed Activation Reasoning Potential (RAP)<n>RAP identifies cognitive samples by estimating each sample's potential to stimulate genuine multi-modal reasoning.<n>Our RAP method consistently achieves superior performance using only 9.3% of the training data, while reducing computational costs by over 43%.
  arXiv  Detail & Related papers  (2025-06-05T08:40:24Z)
• Exploring and Evaluating Multimodal Knowledge Reasoning Consistency of Multimodal Large Language Models [52.569132872560814]
  multimodal large language models (MLLMs) have achieved significant breakthroughs, enhancing understanding across text and vision. However, current MLLMs still face challenges in effectively integrating knowledge across these modalities during multimodal knowledge reasoning. We analyze and compare the extent of consistency degradation in multimodal knowledge reasoning within MLLMs.
  arXiv  Detail & Related papers  (2025-03-03T09:01:51Z)
• Are Large Language Models Good Data Preprocessors? [5.954202581988127]
  High-quality textual training data is essential for the success of multimodal data processing tasks.<n> outputs from image captioning models like BLIP and GIT often contain errors and anomalies that are difficult to rectify using rule-based methods.
  arXiv  Detail & Related papers  (2025-02-24T02:57:21Z)
• Multimodal Inconsistency Reasoning (MMIR): A New Benchmark for Multimodal Reasoning Models [26.17300490736624]
  Multimodal Large Language Models (MLLMs) are predominantly trained and tested on consistent visual-textual inputs.<n>We propose the Multimodal Inconsistency Reasoning benchmark to assess MLLMs' ability to detect and reason about semantic mismatches.<n>We evaluate six state-of-the-art MLLMs, showing that models with dedicated multimodal reasoning capabilities, such as o1, substantially outperform their counterparts.
  arXiv  Detail & Related papers  (2025-02-22T01:52:37Z)
• Large Language Models are Few-shot Multivariate Time Series Classifiers [23.045734479292356]
  Large Language Models (LLMs) have been extensively applied in time series analysis. Yet, their utility in the few-shot classification (i.e., a crucial training scenario) is underexplored. We aim to leverage the extensive pre-trained knowledge in LLMs to overcome the data scarcity problem.
  arXiv  Detail & Related papers  (2025-01-30T03:59:59Z)
• Exploring Large Language Models for Multimodal Sentiment Analysis: Challenges, Benchmarks, and Future Directions [0.0]
  Multimodal Aspect-Based Sentiment Analysis (MABSA) aims to extract aspect terms and their corresponding sentiment polarities from multimodal information, including text and images. Traditional supervised learning methods have shown effectiveness in this task, but the adaptability of large language models (LLMs) to MABSA remains uncertain. Recent advances in LLMs, such as Llama2, LLaVA, and ChatGPT, demonstrate strong capabilities in general tasks, yet their performance in complex and fine-grained scenarios like MABSA is underexplored.
  arXiv  Detail & Related papers  (2024-11-23T02:17:10Z)
• FedMLLM: Federated Fine-tuning MLLM on Multimodal Heterogeneity Data [64.50893177169996]
  Fine-tuning Multimodal Large Language Models (MLLMs) with Federated Learning (FL) allows for expanding the training data scope by including private data sources. We introduce a benchmark for evaluating various downstream tasks in the federated fine-tuning of MLLMs within multimodal heterogeneous scenarios. We develop a general FedMLLM framework that integrates four representative FL methods alongside two modality-agnostic strategies.
  arXiv  Detail & Related papers  (2024-11-22T04:09:23Z)
• LLaVA-KD: A Framework of Distilling Multimodal Large Language Models [70.19607283302712]
  We propose a novel framework to transfer knowledge from l-MLLM to s-MLLM. Specifically, we introduce Multimodal Distillation (MDist) to minimize the divergence between the visual-textual output distributions of l-MLLM and s-MLLM. We also propose a three-stage training scheme to fully exploit the potential of s-MLLM.
  arXiv  Detail & Related papers  (2024-10-21T17:41:28Z)
• Beyond Binary: Towards Fine-Grained LLM-Generated Text Detection via Role Recognition and Involvement Measurement [51.601916604301685]
  Large language models (LLMs) generate content that can undermine trust in online discourse. Current methods often focus on binary classification, failing to address the complexities of real-world scenarios like human-AI collaboration. To move beyond binary classification and address these challenges, we propose a new paradigm for detecting LLM-generated content.
  arXiv  Detail & Related papers  (2024-10-18T08:14:10Z)
• Understanding the Role of LLMs in Multimodal Evaluation Benchmarks [77.59035801244278]
  This paper investigates the role of the Large Language Model (LLM) backbone in Multimodal Large Language Models (MLLMs) evaluation. Our study encompasses four diverse MLLM benchmarks and eight state-of-the-art MLLMs. Key findings reveal that some benchmarks allow high performance even without visual inputs and up to 50% of error rates can be attributed to insufficient world knowledge in the LLM backbone.
  arXiv  Detail & Related papers  (2024-10-16T07:49:13Z)
• MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models [71.36392373876505]
  We introduce MMIE, a large-scale benchmark for evaluating interleaved multimodal comprehension and generation in Large Vision-Language Models (LVLMs)<n>MMIE comprises 20K meticulously curated multimodal queries, spanning 3 categories, 12 fields, and 102 subfields, including mathematics, coding, physics, literature, health, and arts.<n>It supports both interleaved inputs and outputs, offering a mix of multiple-choice and open-ended question formats to evaluate diverse competencies.
  arXiv  Detail & Related papers  (2024-10-14T04:15:00Z)
• Towards Data Contamination Detection for Modern Large Language Models: Limitations, Inconsistencies, and Oracle Challenges [3.0455427910850785]
  We evaluate five contamination detection approaches with four state-of-the-art LLMs across eight challenging datasets. Our analysis reveals that current methods have non-trivial limitations in their assumptions and practical applications.
  arXiv  Detail & Related papers  (2024-09-16T02:04:33Z)
• CoMMIT: Coordinated Instruction Tuning for Multimodal Large Language Models [68.64605538559312]
  In this paper, we analyze the MLLM instruction tuning from both theoretical and empirical perspectives. Inspired by our findings, we propose a measurement to quantitatively evaluate the learning balance. In addition, we introduce an auxiliary loss regularization method to promote updating of the generation distribution of MLLMs.
  arXiv  Detail & Related papers  (2024-07-29T23:18:55Z)
• LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models [71.8065384742686]
  LMMS-EVAL is a unified and standardized multimodal benchmark framework with over 50 tasks and more than 10 models.<n>LMMS-EVAL LITE is a pruned evaluation toolkit that emphasizes both coverage and efficiency.<n>Multimodal LIVEBENCH utilizes continuously updating news and online forums to assess models' generalization abilities in the wild.
  arXiv  Detail & Related papers  (2024-07-17T17:51:53Z)
• The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective [53.48484062444108]
  We find that the development of models and data is not two separate paths but rather interconnected. On the one hand, vaster and higher-quality data contribute to better performance of MLLMs; on the other hand, MLLMs can facilitate the development of data. To promote the data-model co-development for MLLM community, we systematically review existing works related to MLLMs from the data-model co-development perspective.
  arXiv  Detail & Related papers  (2024-07-11T15:08:11Z)
• A Comprehensive Survey of Contamination Detection Methods in Large Language Models [68.10605098856087]
  With the rise of Large Language Models (LLMs) in recent years, abundant new opportunities are emerging, but also new challenges. LLMs' performance may not be reliable anymore, as the high performance may be at least partly due to their previous exposure to the data. This limitation jeopardizes real capability improvement in the field of NLP, yet there remains a lack of methods on how to efficiently detect contamination.
  arXiv  Detail & Related papers  (2024-03-31T14:32:02Z)
• KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models [53.84677081899392]
  KIEval is a Knowledge-grounded Interactive Evaluation framework for large language models. It incorporates an LLM-powered "interactor" role for the first time to accomplish a dynamic contamination-resilient evaluation. Extensive experiments on seven leading LLMs across five datasets validate KIEval's effectiveness and generalization.
  arXiv  Detail & Related papers  (2024-02-23T01:30:39Z)
• GenCeption: Evaluate Multimodal LLMs with Unlabeled Unimodal Data [3.08543976986593]
  Multimodal Large Language Models (MLLMs) are typically assessed using expensive annotated multimodal benchmarks. This paper outlines and validates GenCeption, a novel, annotation-free evaluation method. It requires only unimodal data to measure inter-modality semantic coherence and inversely assesses MLLMs' tendency to hallucinate.
  arXiv  Detail & Related papers  (2024-02-22T21:22:04Z)
• OPDAI at SemEval-2024 Task 6: Small LLMs can Accelerate Hallucination Detection with Weakly Supervised Data [1.3981625092173873]
  This paper describes a unified system for hallucination detection of LLMs. It wins the second prize in the model-agnostic track of the SemEval-2024 Task 6.
  arXiv  Detail & Related papers  (2024-02-20T11:01:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.