Imagen de Portada

Auditing Frontier Vision-Language Models for Trustworthy Medical VQA: Grounding Failures, Format Collapse, and Domain Adaptation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Xupeng, Shi, Binbin, Le, Chenqian, Yin, Qifu, Lin, Lang, Ni, Haowei, Gong, Ran, Li, Panfeng
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMs
por: Le, Chenqian, et al.
Publicado: (2025)

Iterative Multimodal Retrieval-Augmented Generation for Medical Question Answering
por: Chen, Xupeng, et al.
Publicado: (2026)

Harnessing Earnings Reports for Stock Predictions: A QLoRA-Enhanced LLM Approach
por: Ni, Haowei, et al.
Publicado: (2024)

Enhancing Exchange Rate Forecasting with Explainable Deep Learning Models
por: Meng, Shuchen, et al.
Publicado: (2024)

Time Series Modeling for Heart Rate Prediction: From ARIMA to Transformers
por: Ni, Haowei, et al.
Publicado: (2024)

Unified and Semantically Grounded Domain Adaptation for Medical Image Segmentation
por: Wang, Xin, et al.
Publicado: (2025)

Evaluating Modern Approaches in 3D Scene Reconstruction: NeRF vs Gaussian-Based Methods
por: Zhou, Yiming, et al.
Publicado: (2024)

VoxelFormer: Parameter-Efficient Multi-Subject Visual Decoding from fMRI
por: Le, Chenqian, et al.
Publicado: (2025)

On the Role of Visual Grounding in VQA
por: Reich, Daniel, et al.
Publicado: (2024)

Explainable Information Retrieval in the Audit Domain
por: Frummet, Alexander, et al.
Publicado: (2025)

CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
por: Ma, Dongsheng, et al.
Publicado: (2026)

Towards Trustworthy Unsupervised Domain Adaptation: A Representation Learning Perspective for Enhancing Robustness, Discrimination, and Generalization
por: Yin, Jia-Li, et al.
Publicado: (2024)

MedXplain-VQA: Multi-Component Explainable Medical Visual Question Answering
por: Nguyen, Hai-Dang, et al.
Publicado: (2025)

SURE-VQA: Systematic Understanding of Robustness Evaluation in Medical VQA Tasks
por: Kahl, Kim-Celine, et al.
Publicado: (2024)

CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
por: Xia, Peng, et al.
Publicado: (2024)

R-LLaVA: Improving Med-VQA Understanding through Visual Region of Interest
por: Chen, Xupeng, et al.
Publicado: (2024)

Tri-VQA: Triangular Reasoning Medical Visual Question Answering for Multi-Attribute Analysis
por: Fan, Lin, et al.
Publicado: (2024)

Tackling Dimensional Collapse toward Comprehensive Universal Domain Adaptation
por: Fang, Hung-Chieh, et al.
Publicado: (2024)

Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models
por: Zhu, Wenhui, et al.
Publicado: (2025)

Measuring Faithful and Plausible Visual Grounding in VQA
por: Reich, Daniel, et al.
Publicado: (2023)

MedSkillAudit: A Domain-Specific Audit Framework for Medical Research Agent Skills
por: Hou, Yingyong, et al.
Publicado: (2026)

DeferredSeg: A Multi-Expert Deferral Framework for Trustworthy Medical Image Segmentation
por: Tian, Qiuyu, et al.
Publicado: (2026)

Comparison of sEMG Encoding Accuracy Across Speech Modes Using Articulatory and Phoneme Features
por: Le, Chenqian, et al.
Publicado: (2026)

Stage-Audit: Auditable Source-Frontier Discovery for Cross-Wiki Tables
por: Shen, Chen
Publicado: (2026)

RCS-SF-001 — Systemic Failure Under Recoverability Constraints: Cross-Domain Collapse and Unified Failure Pattern
por: Sanchez, Noelia, et al.
Publicado: (2026)

Self-Supervised Anatomical Consistency Learning for Vision-Grounded Medical Report Generation
por: Yang, Longzhen, et al.
Publicado: (2025)

A Review of Electromagnetic Elimination Methods for low-field portable MRI scanner
por: Bian, Wanyu, et al.
Publicado: (2024)

ToolVQA: A Dataset for Multi-step Reasoning VQA with External Tools
por: Yin, Shaofeng, et al.
Publicado: (2025)

Safe Reinforcement Learning Beyond Baseline Control: A Hierarchical Framework for Space Triangle Tethered Formation System
por: Tao, Xinyi, et al.
Publicado: (2026)

CoTBox-TTT: Grounding Medical VQA with Visual Chain-of-Thought Boxes During Test-time Training
por: Qian, Jiahe, et al.
Publicado: (2025)

Visual Grounding Methods for VQA are Working for the Wrong Reasons!
por: Shrestha, Robik, et al.
Publicado: (2020)

Uncovering the Full Potential of Visual Grounding Methods in VQA
por: Reich, Daniel, et al.
Publicado: (2024)

DVLTA-VQA: Decoupled Vision-Language Modeling with Text-Guided Adaptation for Blind Video Quality Assessment
por: Yu, Li, et al.
Publicado: (2025)

Abduction of Domain Relationships from Data for VQA
por: Chowdhury, Al Mehdi Saadat, et al.
Publicado: (2025)

Large Language models for Time Series Analysis: Techniques, Applications, and Challenges
por: Shi, Feifei, et al.
Publicado: (2025)

DDFP: Data-dependent Frequency Prompt for Source Free Domain Adaptation of Medical Image Segmentation
por: Yin, Siqi, et al.
Publicado: (2025)

SemiDAViL: Semi-supervised Domain Adaptation with Vision-Language Guidance for Semantic Segmentation
por: Basak, Hritam, et al.
Publicado: (2025)

Few-Shot Adaptation of Grounding DINO for Agricultural Domain
por: Singh, Rajhans, et al.
Publicado: (2025)

Multi-Task Learning for Visually Grounded Reasoning in Gastrointestinal VQA
por: Safwan, Itbaan, et al.
Publicado: (2025)

Entropy Minimization without Model Collapse: Mitigating Prediction Bias in Medical Imaging
por: Nielen, Tim, et al.
Publicado: (2026)