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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Karim, A H M Rezaul, Uzuner, Ozlem
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908596583792640
author Karim, A H M Rezaul
Uzuner, Ozlem
author_facet Karim, A H M Rezaul
Uzuner, Ozlem
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13856
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multimodal Retrieval-Augmented Generation with Large Language Models for Medical VQA
Karim, A H M Rezaul
Uzuner, Ozlem
Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
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.
title Multimodal Retrieval-Augmented Generation with Large Language Models for Medical VQA
topic Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.13856