cs.AINov 18, 2026

When Figures Disagree with Text: Evaluating Autonomous Visual Evidence Verification in Scientific Papers

Authors: Guijia Zhang, Hongbo Qiu, Jiajun Zha, Guohao Cai, Hao Zheng, Huihao Jing, Kexu Cheng, Shipeng Luo, 

Organizations: The Hong Kong University of Science and Technology · Shenzhen University · xgenlabs · Institute of Computing Technology, Chinese Academy of Sciences · 

Abstract

Scientific figures carry evidence for the claims that cite them, so reviewing a paper means checking that a figure agrees with the text, and not only describing what the figure shows. Benchmarks of figure-text verification typically hand the model the figure, the claim, or the knowledge that an inconsistency exists, which leaves untested whether a model can find the figure worth checking in a complete paper, relate a visual element to the claim it conflicts with, and recognize the conflict. We study this autonomous setting on 31 full manuscripts, each carrying a reviewer-documented figure-text inconsistency from PRISMM-Bench that is hidden from the model. Six multimodal models review each PDF under a neutral prompt, and we then add one input at a time to the same manuscripts. Of 1,445 open-ended reviews, 60.6% mention the flawed figure, yet a grading rubric accepts only 3.3% as diagnosing its contradiction; a blind audit finds the rubric lenient, so we read these as rubric-accepted rates and compare conditions rather than absolute values. In a separate controlled run, naming the figure, without stating that it is flawed, raises rubric-accepted diagnosis from 4.3% to 20.4%, while a consistency instruction and coarse visual cues do not. When the contradiction is visible only in the rendered figure, text-only review yields no accepted diagnosis, while review of the rendered pages with the figure named reaches 15.8%. A baseline that lets the model choose which figures to check, ranked by centrality, stays at 4.8%. Deciding what to verify is thus a large part of the difficulty, and the selection rule we tested does not resolve it. Multimodal document understanding should be evaluated on whether a model can propose what to verify, not only answer questions about a figure it is handed.

Figures & tables

Appendix figures & tables19 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. SciFigPlag-Bench: A Benchmark for Provenance-Aware Scientific Figure Plagiarism Detection

    Jul 31, 2026Zhiying Cui, Minghao Yang, Linlin Gao +2VLM EvaluationImage Forgery Detection

  2. SciFigAlign: Scoring Scientific Figures by Fine-tuned Alignment of Visuals with Manuscript Evidence

    Jul 29, 2026Chuanzhi Xu, Zihan Deng, Huiqi Liang +4Scholarly Peer ReviewImage Quality Assessment

  3. SciFigDetect: A Benchmark for AI-Generated Scientific Figure Detection

    Apr 9, 2026You Hu, Chenzhuo Zhao, Changfa Mo +2AI-Generated Image DetectionDigital Image Forensics