# Multimodal Retrieval-Augmented Generation with Large Language Models for Medical VQA

Source: [Multimodal Retrieval-Augmented Generation with Large Language Models for Medical VQA](<https://www.sota2.com/research/paper/68fa7c331e209131cea8cfc7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:59:10.201Z

Authors: A H M Rezaul Karim, Ozlem Uzuner

Published: 2025-10-12T07:03:58.000Z

## Abstract

Medical Visual Question Answering (MedVQA) enables natural language queries over medical images to support clinical decision-making and patient care. The MEDIQA-WV 2025 shared task addressed wound-care VQA, requiring systems to generate free-text responses and structured wound attributes from images and patient queries. We present the MasonNLP system, which employs a general-domain, instruction-tuned large language model with a retrieval-augmented generation (RAG) framework that incorporates textual and visual examples from in-domain data. This approach grounds outputs in clinically relevant exemplars, improving reasoning, schema adherence, and response quality across dBLEU, ROUGE, BERTScore, and LLM-based metrics. Our best-performing system ranked 3rd among 19 teams and 51 submissions with an average score of 41.37%, demonstrating that lightweight RAG with general-purpose LLMs -- a minimal inference-time layer that adds a few relevant exemplars via simple indexing and fusion, with no extra training or complex re-ranking -- provides a simple and effective baseline for multimodal clinical NLP tasks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2510.13856>)

[PDF](<https://arxiv.org/pdf/2510.13856.pdf>)
