Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Byun, Ji Young, Park, Young-Jin, Corbeil, Jean-Philippe, Abacha, Asma Ben
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Improving Medical VQA through Trajectory-Aware Process Supervision
par: Gulluk, Halil Ibrahim, et autres
Publié: (2026)

SURE-VQA: Systematic Understanding of Robustness Evaluation in Medical VQA Tasks
par: Kahl, Kim-Celine, et autres
Publié: (2024)

Known Meets Unknown: Mitigating Overconfidence in Open Set Recognition
par: Zhao, Dongdong, et autres
Publié: (2025)

FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA
par: Sarwar, Nobin
Publié: (2025)

VGS-Decoding: Visual Grounding Score Guided Decoding for Hallucination Mitigation in Medical VLMs
par: Kolli, Govinda, et autres
Publié: (2026)

Look Closer! An Adversarial Parametric Editing Framework for Hallucination Mitigation in VLMs
par: Hu, Jiayu, et autres
Publié: (2025)

Efficient High-Resolution Image Editing with Hallucination-Aware Loss and Adaptive Tiling
par: Kwon, Young D., et autres
Publié: (2025)

ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models
par: Park, Yeji, et autres
Publié: (2024)

Optimal Transport-Induced Samples against Out-of-Distribution Overconfidence
par: Tang, Keke, et autres
Publié: (2026)

Mitigating Diffusion Model Hallucinations with Dynamic Guidance
par: Triaridis, Kostas, et autres
Publié: (2025)

Bridging the Semantic Gaps: Improving Medical VQA Consistency with LLM-Augmented Question Sets
par: Ma, Yongpei, et autres
Publié: (2025)

Refine and Align: Confidence Calibration through Multi-Agent Interaction in VQA
par: Pandey, Ayush, et autres
Publié: (2025)

Online Self-Calibration Against Hallucination in Vision-Language Models
par: Chen, Minghui, et autres
Publié: (2026)

Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations
par: Jiang, Nick, et autres
Publié: (2024)

Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling
par: Byun, Min Sik, et autres
Publié: (2025)

Mitigating Object Hallucinations in Vision-Language Models through Region-Aware Attention Recalibration
par: Xu, Yuanzhi, et autres
Publié: (2026)

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding
par: Tang, Feilong, et autres
Publié: (2025)

Locate-then-Sparsify: Attribution Guided Sparse Strategy for Visual Hallucination Mitigation
par: Dang, Tiantian, et autres
Publié: (2026)

WildFireVQA: A Large-Scale Radiometric Thermal VQA Benchmark for Aerial Wildfire Monitoring
par: Habibpour, Mobin, et autres
Publié: (2026)

An Empirical Study Into What Matters for Calibrating Vision-Language Models
par: Tu, Weijie, et autres
Publié: (2024)

Test-Time-Scaling for Zero-Shot Diagnosis with Visual-Language Reasoning
par: Byun, Ji Young, et autres
Publié: (2025)

MaskMedPaint: Masked Medical Image Inpainting with Diffusion Models for Mitigation of Spurious Correlations
par: Jin, Qixuan, et autres
Publié: (2024)

Taking Shortcuts for Categorical VQA Using Super Neurons
par: Musacchio, Pierre, et autres
Publié: (2026)

Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression
par: Sarkar, Sreetama, et autres
Publié: (2025)

VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding
par: Li, Zongxia, et autres
Publié: (2025)

HaloProbe: Bayesian Detection and Mitigation of Object Hallucinations in Vision-Language Models
par: Zohrabi, Reihaneh, et autres
Publié: (2026)

Interpolation of GEDI Biomass Estimates with Calibrated Uncertainty Quantification
par: Young, Robin, et autres
Publié: (2026)

Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training
par: Choi, Yujin, et autres
Publié: (2024)

Disentanglement-Based Equivariant Learning for Compositional VQA
par: Du, Zhou, et autres
Publié: (2026)

Unexplored flaws in multiple-choice VQA evaluations
par: Rosenthal, Fabio, et autres
Publié: (2025)

BERT-VQA: Visual Question Answering on Plots
par: Vu, Tai, et autres
Publié: (2025)

VQA-Levels: A Hierarchical Approach for Classifying Questions in VQA
par: Madaka, Madhuri Latha, et autres
Publié: (2025)

Optimizing Calibration by Gaining Aware of Prediction Correctness
par: Liu, Yuchi, et autres
Publié: (2024)

Reducing catastrophic forgetting of incremental learning in the absence of rehearsal memory with task-specific token
par: Choi, Young Jo, et autres
Publié: (2024)

Laplacian Score Sharpening for Mitigating Hallucination in Diffusion Models
par: C, Barath Chandran., et autres
Publié: (2025)

Hallucinatory Image Tokens: A Training-free EAZY Approach on Detecting and Mitigating Object Hallucinations in LVLMs
par: Che, Liwei, et autres
Publié: (2025)

Multi-Task Learning for Visually Grounded Reasoning in Gastrointestinal VQA
par: Safwan, Itbaan, et autres
Publié: (2025)

Frequency-Calibrated Membership Inference Attacks on Medical Image Diffusion Models
par: Zhao, Xinkai, et autres
Publié: (2025)

Overconfidence is Key: Verbalized Uncertainty Evaluation in Large Language and Vision-Language Models
par: Groot, Tobias, et autres
Publié: (2024)

RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models
par: Zhang, Serena, et autres
Publié: (2024)