@inproceedings{karim-uzuner-2025-masonnlp-mediqa,
title = "{M}ason{NLP} at {MEDIQA}-{WV} 2025: Multimodal Retrieval-Augmented Generation with Large Language Models for Medical {VQA}",
author = "Karim, A H M Rezaul and
Uzuner, Ozlem",
editor = "Ben Abacha, Asma and
Bethard, Steven and
Bitterman, Danielle and
Naumann, Tristan and
Roberts, Kirk",
booktitle = "Proceedings of the 7th Clinical Natural Language Processing Workshop",
month = oct,
year = "2025",
address = "Virtual",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.clinicalnlp-1.10/",
pages = "84--94",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="karim-uzuner-2025-masonnlp-mediqa">
<titleInfo>
<title>MasonNLP at MEDIQA-WV 2025: Multimodal Retrieval-Augmented Generation with Large Language Models for Medical VQA</title>
</titleInfo>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">H</namePart>
<namePart type="given">M</namePart>
<namePart type="given">Rezaul</namePart>
<namePart type="family">Karim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ozlem</namePart>
<namePart type="family">Uzuner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Clinical Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Ben Abacha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danielle</namePart>
<namePart type="family">Bitterman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Virtual</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">karim-uzuner-2025-masonnlp-mediqa</identifier>
<location>
<url>https://aclanthology.org/2025.clinicalnlp-1.10/</url>
</location>
<part>
<date>2025-10</date>
<extent unit="page">
<start>84</start>
<end>94</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MasonNLP at MEDIQA-WV 2025: Multimodal Retrieval-Augmented Generation with Large Language Models for Medical VQA
%A Karim, A. H. M. Rezaul
%A Uzuner, Ozlem
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Bitterman, Danielle
%Y Naumann, Tristan
%Y Roberts, Kirk
%S Proceedings of the 7th Clinical Natural Language Processing Workshop
%D 2025
%8 October
%I Association for Computational Linguistics
%C Virtual
%F karim-uzuner-2025-masonnlp-mediqa
%X 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.
%U https://aclanthology.org/2025.clinicalnlp-1.10/
%P 84-94
Markdown (Informal)
[MasonNLP at MEDIQA-WV 2025: Multimodal Retrieval-Augmented Generation with Large Language Models for Medical VQA](https://aclanthology.org/2025.clinicalnlp-1.10/) (Karim & Uzuner, ClinicalNLP 2025)
ACL