arXiv Computer Vision September 25, 2026 By Keyang Zhou, Siyi Li, Zhongnan Shi, Qichao Ying, Wei Tang, Zhenxing Qian

PROVE: Proof-guided Regime-aware Operator Verification for Hallucination Detection in Medical Visual Question Answering

Read the original on arXiv Computer Vision →

PROVE is a black‑box hallucination detector for medical visual question answering that tailors its verification strategy to each question’s evidential structure. It classifies questions into three regimes, activates a subset of five operators per regime, and calibrates operator importance using deterministic question‑answer features to produce a risk score. On 8048 test samples across three medical VQA benchmarks and four state‑of‑the‑art vision‑language models, PROVE achieves an AUROC of 0.821, surpassing the best baseline by 0.159 with consistent improvements across all models and datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI

Aug 14

Polish Medical Visual Question Answering: Vision-Language Models Underutilize Visual Evidence

arXiv:2608. 12928v1 Announce Type: new Abstract: We introduce a Polish-language medical visual question answering (VQA) benchmark, built from Polish Board Certification Examination questions for licensed physicians and dentists pursuing specialist certification.

By Jakub Pokrywka, {\L}ukasz Grzybowski, Antoni Lasik, Marek Kubis, Jeremi Ignacy Kaczmarek, Wojciech Kusa

llms nlp multimodal benchmarks

arXiv Computer Vision

3d ago

Overconfidence and Calibration in Medical VQA: Empirical Findings and Hallucination-Aware Mitigation

arXiv:2604.02543v2 Announce Type: replace Abstract: As vision-language models (VLMs) are increasingly deployed in clinical decision support, more than accuracy is required: knowing when to trust thei...

By Ji Young Byun, Young-Jin Park, Jean-Philippe Corbeil, Asma Ben Abacha

llms nlp multimodal benchmarks safety

arXiv Computation and Language

Sep 4

Uncertainty Is Not a Safety Net for Clinical VQA, but Can It Anticipate Model Failure?

The paper evaluates uncertainty estimation (UE) methods for clinical vision‑language models (VLMs) on visual question answering (VQA). Across 8 UE techniques and 12 VLMs, UE quality tracks model accuracy, degrading where performance is weakest, and fails to signal uncertainty when models are stressed by hiding the correct answer (NOTA perturbations). However, UE on unperturbed inputs reliably predicts which predictions will collapse under NOTA, suggesting UE can diagnose model fragility.

By Arnisa Fazla, Alberto Testoni, Ameen Abu-Hanna, Barbara Plank, Iacer Calixto

llms multimodal benchmarks safety

arXiv AI

Jul 21

Deterministic Hallucination Detection in Medical VQA via Confidence-Evidence Bayesian Gain

arXiv:2603. 21693v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have shown strong potential for medical Visual Question Answering (VQA), yet they remain prone to hallucinations, defined as generating responses that contradict the input image, posing serious risks in clinical settings.

By Mohammad Asadi, Tahoura Nedaee, Jack W. O'Sullivan, Euan Ashley, Ehsan Adeli

llms nlp multimodal benchmarks safety

arXiv Machine Learning

Sep 10

Separating Capability from Confidence: Grounded Dual-State Calibration for GRPO-Trained Medical Vision-Language Models

arXiv:2609.06419v1 Announce Type: cross Abstract: Medical vision-language models (VLMs) require confidence that reflects both answer correctness and patient-specific visual evidence. Recent GRPO-base...

By Yangyang Xie, Ke Hao, Jiaqi Liu, Yun Gu, Xinglin Zhang

llms multimodal benchmarks

arXiv AI

Jul 21

MedLVR: Latent Visual Reasoning for Reliable Medical Visual Question Answering

arXiv:2604. 09757v2 Announce Type: replace-cross Abstract: Medical vision--language models (VLMs) have shown strong potential for medical visual question answering (VQA), yet their reasoning remains largely text-centric: images are encoded once as static context, and subsequent inference is dominated by language.

By Suyang Xi, Songtao Hu, Yuxiang Lai, Wangyun Dan, Yaqi Liu, Shansong Wang, Xiaofeng Yang

llms rag nlp fine-tuning benchmarks

One email a morning, machine-written

Related stories

Polish Medical Visual Question Answering: Vision-Language Models Underutilize Visual Evidence

Overconfidence and Calibration in Medical VQA: Empirical Findings and Hallucination-Aware Mitigation

Uncertainty Is Not a Safety Net for Clinical VQA, but Can It Anticipate Model Failure?

Deterministic Hallucination Detection in Medical VQA via Confidence-Evidence Bayesian Gain

Separating Capability from Confidence: Grounded Dual-State Calibration for GRPO-Trained Medical Vision-Language Models

MedLVR: Latent Visual Reasoning for Reliable Medical Visual Question Answering