Saved in:
Bibliographic Details
Main Authors: Jin, Ruinan, Zhao, Beidi, Kang, Myeongkyun, Zhang, Qiong, Li, Xiaoxiao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.10850
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917481070723072
author Jin, Ruinan
Zhao, Beidi
Kang, Myeongkyun
Zhang, Qiong
Li, Xiaoxiao
author_facet Jin, Ruinan
Zhao, Beidi
Kang, Myeongkyun
Zhang, Qiong
Li, Xiaoxiao
contents Self-verification, re-invoking the same vision language model (VLM) in a fresh context to check its own generated answer, is increasingly used as a default safety layer for medical visual question answering (VQA). We argue that this practice is fundamentally unreliable. We introduce [METHOD NAME], a diagnostic framework for mapping the reliability boundary of medical VLM self-verification by decomposing verifier behavior into discrimination capability and agreement bias. Because the verifier and answer generator are capacity-coupled, the verifier can overly agree with the generator, creating a verification mirage: a regime with both high verifier error and high agreement bias, driven by false acceptance of incorrect answers. Evaluating six open-weight VLMs across five medical VQA datasets and seven medical tasks, we find that this boundary is strongly task-conditioned. Knowledge-intensive clinical tasks fall deepest into the mirage, simpler tasks are more resistant, and perceptual tasks lie in between. Verification also fails to provide an independent safety signal: logistic mixed-effects analysis shows that verifier error and agreement bias become more likely when the generator is wrong, while saliency analyses show that verifiers under-attend to image evidence relative to generators, a phenomenon we call the lazy verifier. Cross-verification reduces but does not eliminate the mirage. Moreover, when verification is reused in multi-turn actor-verifier loops, most initially wrong answers become locked in by false verification. Since our experiments use clean benchmarks, the observed reliability boundary likely underestimates failures in real clinical deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2605_10850
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Verification Mirage: Mapping the Reliability Boundary of Self-Verification in Medical VQA
Jin, Ruinan
Zhao, Beidi
Kang, Myeongkyun
Zhang, Qiong
Li, Xiaoxiao
Computer Vision and Pattern Recognition
Self-verification, re-invoking the same vision language model (VLM) in a fresh context to check its own generated answer, is increasingly used as a default safety layer for medical visual question answering (VQA). We argue that this practice is fundamentally unreliable. We introduce [METHOD NAME], a diagnostic framework for mapping the reliability boundary of medical VLM self-verification by decomposing verifier behavior into discrimination capability and agreement bias. Because the verifier and answer generator are capacity-coupled, the verifier can overly agree with the generator, creating a verification mirage: a regime with both high verifier error and high agreement bias, driven by false acceptance of incorrect answers. Evaluating six open-weight VLMs across five medical VQA datasets and seven medical tasks, we find that this boundary is strongly task-conditioned. Knowledge-intensive clinical tasks fall deepest into the mirage, simpler tasks are more resistant, and perceptual tasks lie in between. Verification also fails to provide an independent safety signal: logistic mixed-effects analysis shows that verifier error and agreement bias become more likely when the generator is wrong, while saliency analyses show that verifiers under-attend to image evidence relative to generators, a phenomenon we call the lazy verifier. Cross-verification reduces but does not eliminate the mirage. Moreover, when verification is reused in multi-turn actor-verifier loops, most initially wrong answers become locked in by false verification. Since our experiments use clean benchmarks, the observed reliability boundary likely underestimates failures in real clinical deployment.
title Verification Mirage: Mapping the Reliability Boundary of Self-Verification in Medical VQA
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.10850