@inproceedings{garcia-lithgow-serrano-2024-neui,
title = "{NEUI} at {MEDIQA}-{M}3{G} 2024: Medical {VQA} through consensus",
author = "Garc{\'\i}a, Ricardo and
Lithgow-Serrano, Oscar",
editor = "Naumann, Tristan and
Ben Abacha, Asma and
Bethard, Steven and
Roberts, Kirk and
Bitterman, Danielle",
booktitle = "Proceedings of the 6th Clinical Natural Language Processing Workshop",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.clinicalnlp-1.45",
doi = "10.18653/v1/2024.clinicalnlp-1.45",
pages = "448--460",
abstract = "This document describes our solution to the MEDIQA-M3G: Multilingual {\&} Multimodal Medical Answer Generation. To build our solution, we leveraged two pre-trained models, a Visual Language Model (VLM) and a Large Language Model (LLM). We fine-tuned both models using the MEDIQA-M3G and MEDIQA-CORR training datasets, respectively. In the first stage, the VLM provides singular responses for each pair of image {\&} text inputs in a case. In the second stage, the LLM consolidates the VLM responses using it as context among the original text input. By changing the original English case content field in the context component of the second stage to the one in Spanish, we adapt the pipeline to generate submissions in English and Spanish. We performed an ablation study to explore the impact of the different models{'} capabilities, such as multimodality and reasoning, on the MEDIQA-M3G task. Our approach favored privacy and feasibility by adopting open-source and self-hosted small models and ranked 4th in English and 2nd in Spanish.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garcia-lithgow-serrano-2024-neui">
<titleInfo>
<title>NEUI at MEDIQA-M3G 2024: Medical VQA through consensus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">García</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oscar</namePart>
<namePart type="family">Lithgow-Serrano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Clinical Natural Language Processing Workshop</title>
</titleInfo>
<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">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">Kirk</namePart>
<namePart type="family">Roberts</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This document describes our solution to the MEDIQA-M3G: Multilingual & Multimodal Medical Answer Generation. To build our solution, we leveraged two pre-trained models, a Visual Language Model (VLM) and a Large Language Model (LLM). We fine-tuned both models using the MEDIQA-M3G and MEDIQA-CORR training datasets, respectively. In the first stage, the VLM provides singular responses for each pair of image & text inputs in a case. In the second stage, the LLM consolidates the VLM responses using it as context among the original text input. By changing the original English case content field in the context component of the second stage to the one in Spanish, we adapt the pipeline to generate submissions in English and Spanish. We performed an ablation study to explore the impact of the different models’ capabilities, such as multimodality and reasoning, on the MEDIQA-M3G task. Our approach favored privacy and feasibility by adopting open-source and self-hosted small models and ranked 4th in English and 2nd in Spanish.</abstract>
<identifier type="citekey">garcia-lithgow-serrano-2024-neui</identifier>
<identifier type="doi">10.18653/v1/2024.clinicalnlp-1.45</identifier>
<location>
<url>https://aclanthology.org/2024.clinicalnlp-1.45</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>448</start>
<end>460</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NEUI at MEDIQA-M3G 2024: Medical VQA through consensus
%A García, Ricardo
%A Lithgow-Serrano, Oscar
%Y Naumann, Tristan
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Roberts, Kirk
%Y Bitterman, Danielle
%S Proceedings of the 6th Clinical Natural Language Processing Workshop
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F garcia-lithgow-serrano-2024-neui
%X This document describes our solution to the MEDIQA-M3G: Multilingual & Multimodal Medical Answer Generation. To build our solution, we leveraged two pre-trained models, a Visual Language Model (VLM) and a Large Language Model (LLM). We fine-tuned both models using the MEDIQA-M3G and MEDIQA-CORR training datasets, respectively. In the first stage, the VLM provides singular responses for each pair of image & text inputs in a case. In the second stage, the LLM consolidates the VLM responses using it as context among the original text input. By changing the original English case content field in the context component of the second stage to the one in Spanish, we adapt the pipeline to generate submissions in English and Spanish. We performed an ablation study to explore the impact of the different models’ capabilities, such as multimodality and reasoning, on the MEDIQA-M3G task. Our approach favored privacy and feasibility by adopting open-source and self-hosted small models and ranked 4th in English and 2nd in Spanish.
%R 10.18653/v1/2024.clinicalnlp-1.45
%U https://aclanthology.org/2024.clinicalnlp-1.45
%U https://doi.org/10.18653/v1/2024.clinicalnlp-1.45
%P 448-460
Markdown (Informal)
[NEUI at MEDIQA-M3G 2024: Medical VQA through consensus](https://aclanthology.org/2024.clinicalnlp-1.45) (García & Lithgow-Serrano, ClinicalNLP-WS 2024)
ACL