CheXPoT: Post-Hoc Visual Verification and Correction of VLM-Generated Radiology Reports
cs.CL, cs.CV
Submitted: 2026-10-31
Updated: 2026-10-31
Code: https://github.com/Google-Health/medgemma
Terminology
Sources
- RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models
- Detecting and Evaluating Medical Hallucinations in Large Vision Language Models
- A Vision-Language Foundation Model to Enhance Efficiency of Chest X-ray Interpretation
- MAIRA-2: Grounded Radiology Report Generation
- Hallucination Mitigating for Medical Report Generation
- Direct Preference Optimization for Suppressing Hallucinated Prior Exams in Radiology Report Generation
- The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering
- ReXTrust: A Model for Fine-Grained Hallucination Detection in AI-Generated Radiology Reports
- Hallucination Filtering in Radiology Vision-Language Models Using Discrete Semantic Entropy
- Semantic Consistency-Based Uncertainty Quantification for Factuality in Radiology Report Generation
- MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
- Reasoning Visual Language Model for Chest X-Ray Analysis
- ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verification
- X-Ray-CoT: Interpretable Chest X-ray Diagnosis with Vision-Language Models via Chain-of-Thought Reasoning
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- Pelican: Correcting Hallucination in Vision-LLMs via Claim Decomposition and Program of Thought Verification
- RadGraph: Extracting Clinical Entities and Relations from Radiology Reports
- CheXpert Plus: Augmenting a Large Chest X-ray Dataset with Text Radiology Reports, Patient Demographics and Additional Image Formats
- CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT
- Focal Loss for Dense Object Detection
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data