Article

Ask Twice, Look Twice: Training-Free Consistency Filtering for Reliable Medical VQA

2026-08-20

Abstract excerpt

<title>Abstract</title> <p>Medical Visual Question Answering (MVQA) exhibits significant potential for clinical decision support; however, current vision-language models are prone to producing inconsistent outputs. Standard evaluations rarely test robustness against semantically equivalent paraphrases or visual perturbations, which may lead to overestimating the model’s reliability. In real clinical scenarios, ob...

Topics

Open a Topic to create a Post that cites this publication.

Uncategorized literature

Identifiers and source

Literature Corpus work: 6d481e5f-3b42-57f3-bba5-59b503a8e98e
DOI: 10.21203/rs.3.rs-7867052/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Ask Twice, Look Twice: Training-Free Consistency Filtering for Reliable Medical VQADOI 10.21203/rs.3.rs-7867052/v1Read

Bridging the Semantic Gaps: Improving MVQA Consistency with LLM-Augmented Question SetsSemantic proximity Read

Towards Multimodal Retrieval-Augmented Generation for Medical Visual Question AnsweringSemantic proximity Read

Enhancing Clinical Reasoning in Medical Vision-Language Model through Structured PromptsSemantic proximity Read

MammoVQA: A Benchmark for Breast Cancer Screening and Diagnosis in Mammogram Visual Question AnsweringSemantic proximity Read

Evaluating the performance of large language & visual-language models in cervical cytology screeningSemantic proximity Read

RobustVLM: Enhancing Large Vision-Language Models through Adaptive Visual Context Learning, Weak-to-Strong Robust Transfer, and Domain-Adaptive FeedbackSemantic proximity Read

Domain-Specific Fine-Tuning in a Retrieval-Augmented Generation Framework for Precision Geriatric Medical QASemantic proximity Read

Performance of Multimodal GPT-4V on USMLE with Image: Potential for Imaging Diagnostic Support with ExplanationsSemantic proximity Read

Comparative Analysis of Multimodal Large Language Models GPT-4o and o1 vs Clinicians in Clinical Case Challenge QuestionsSemantic proximity Read

Bridging Medical Imaging and Reports:Learning Radiologist's Nuances via Fine-Grained Multi-Modal AlignmentSemantic proximity Read

Comparative Analysis of GPT-4Vision, GPT-4 and Open Source LLMs in Clinical Diagnostic Accuracy: A Benchmark Against Human ExpertiseSemantic proximity Read

FFA-GPT: an Interactive Visual Question Answering System for Fundus Fluorescein AngiographySemantic proximity Read