# Reducing Hallucinations of Medical Multimodal Large Language Models with Visual Retrieval-Augmented Generation

arXiv: https://arxiv.org/abs/2502.15040 · HTML: https://mlsanity.com/paper/2502.15040/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 2 of its 35 references that are in the map.
- First posted on arXiv 20 Feb 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Hallucination mitigation in LVLMs](https://mlsanity.com/mllm/hallucination-mitigation-in-lvlms/)
- Retrieval-augmented generation / [Medical and biomedical RAG](https://mlsanity.com/rag/medical-and-biomedical-rag/)

## Builds on (most cited first, 2 of 2)

- [Alleviating Hallucination in Large Vision-Language Models with Active Retrieval Augmentation](https://mlsanity.com/paper/2408.00555/) (2024)
- [Hallucination Benchmark in Medical Visual Question Answering](https://mlsanity.com/paper/2401.05827/) (2024)

## Built on by (most cited first, 8 of 8)

- [MMGraphRAG: Bridging Vision and Language with Interpretable Multimodal Knowledge Graphs](https://mlsanity.com/paper/2507.20804/) (2025)
- [RadAgents: Multimodal Agentic Reasoning for Chest X-ray Interpretation with Radiologist-like Workflows](https://mlsanity.com/paper/2509.20490/) (2025)
- [Trustworthy Medical Imaging with Large Language Models: A Study of Hallucinations Across Modalities](https://mlsanity.com/paper/2508.07031/) (2025)
- [Visual Alignment of Medical Vision-Language Models for Grounded Radiology Report Generation](https://mlsanity.com/paper/2512.16201/) (2025)
- [MedVQA-TREE: A Multimodal Reasoning and Retrieval Framework for Sarcopenia Prediction](https://mlsanity.com/paper/2508.19319/) (2025)
- [RAG System for Supporting Japanese Litigation Procedures: Faithful Response Generation Complying with Legal Norms](https://mlsanity.com/paper/2511.22858/) (2025)
- [Concept-Enhanced Multimodal RAG: Towards Interpretable and Accurate Radiology Report Generation](https://mlsanity.com/paper/2602.15650/) (2026)
- [From Image Interpretation to Clinical Reasoning: Upstream Physician-Context-Aware Multimodal Learning with Causal Reinforcement Learning](https://mlsanity.com/paper/2609.38924/) (2026)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) have shown impressive performance in vision and text tasks. However, hallucination remains a major challenge, especially in fields like healthcare where details are critical. In this work, we show how MLLMs may be enhanced to support Visual RAG (V-RAG), a retrieval-augmented generation framework that incorporates both text and visual data from retrieved images. On the MIMIC-CXR chest X-ray report generation and Multicare medical image caption generation datasets, we show that Visual RAG improves the accuracy of entity probing, which asks whether a medical entities is grounded by an image. We show that the improvements extend both to frequent and rare entities, the latter of which may have less positive training data. Downstream, we apply V-RAG with entity probing to correct hallucinations and generate more clinically accurate X-ray reports, obtaining a higher RadGraph-F1 score.