{"ID":2856699,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.13856","arxiv_id":"2510.13856","title":"Multimodal Retrieval-Augmented Generation with Large Language Models for Medical VQA","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.","short_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...","url_abs":"https://arxiv.org/abs/2510.13856","url_pdf":"https://arxiv.org/pdf/2510.13856v1","authors":"[\"A H M Rezaul Karim\",\"Ozlem Uzuner\"]","published":"2025-10-12T07:03:58Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.CV\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","has_code":false}