MétaCan
Menu
Back to cohort

Learning or Cheating? Assessing Data Contamination in Large Vision-Language Models

2025· article· W4415524633 on OpenAlexafffund
Ahmed Masry, M. Firoz Ahmed, Ridwan Mahbub

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsYork University
FundersNatural Sciences and Engineering Research Council of CanadaCanada Foundation for Innovation
KeywordsOverfittingGeneralizationQuestion answeringImage (mathematics)ChartData modelingVisual reasoning

Abstract

fetched live from OpenAlex

Large Vision-Language Models (VLMs) have demonstrated remarkable capabilities in tasks that involve both visual and textual understanding, including chart interpretation, document comprehension, and geometric reasoning. However, concerns remain about whether these models truly generalize or if their performance on popular benchmarks is influenced by overfitting and data contamination. To investigate these concerns, we propose a systematic evaluation framework for assessing data contamination of both closed-source and open-source VLMs using multiple visual question answering benchmarks, including ChartQA, DocVQA, InfoVQA, and MathVista. Our approach applies structured perturbations such as image replacement and question completion to four visual question answering benchmarks (ChartQA, DocVQA, InfoVQA, MathVista). By comparing original and perturbed accuracies, we compute a contamination score that measures how much each model relies on memorized examples versus genuine multimodal reasoning. Our results reveal significant performance shifts and conclude that both closed-source and open-source VLMs suffer from data contamination. These findings underscore the necessity of rigorous data filtering and independent evaluations to ensure robust generalization before deploying VLMs in real-world applications.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.005
metaresearch head score (Gemma)0.004
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Scholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.910
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0050.004
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.003
Science and technology studies0.0010.000
Scholarly communication0.0020.008
Open science0.0030.006
Research integrity0.0000.002
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.031
GPT teacher head0.375
Teacher spread0.344 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes2
Has abstractyes

Explore more

Same topicAdversarial Robustness in Machine LearningFrench-language works237,207