@inproceedings{johnson-etal-2026-lamp,
title = "{LAMP}-{M}ed{QA}: A Lightweight Multi-Agent System for Patient-Oriented Medical Question Answering",
author = "Johnson, Jack A. and
Banerjee, Meghali and
Crawford, Joseph and
Welch, James and
Davies, Jim and
Wang, Tingyan",
editor = "T.Y.S.S., Santosh and
Rodriguez, Juan Diego and
de Gibert, Ona",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-srw.60/",
pages = "663--674",
ISBN = "979-8-89176-393-7",
abstract = "Patient health literacy is critical to health outcomes, yet medical discharge summaries remain inaccessible to many patients due to jargon and complex language. Large language models (LLMs) offer a promising means of bridging this gap, but their deployment in resource-constrained hospital environments demands lightweight, privacy-preserving solutions. We evaluate a range of open- and closed-source LLMs on the MeDiSumQA dataset, comprising real patient discharge summaries paired with lay questions and clinician-verified answers, and demonstrate that larger open-source models achieve accuracy and semantic similarity performance comparable to GPT-5. We then introduce LAMP-MedQA, a lightweight multi-agent framework for patient-oriented medical question answering. The framework decomposes the task into two sequential stages: question-relevant evidence extraction and patient-facing answer simplification. Each stage is governed by an automated, metric-driven feedback loop that enables iterative self-correction without human-in-the-loop supervision. Using Qwen2.5-7B-Instruct for generation agents and Phi-3.5-Mini-Instruct for reviewer/verifier agents, it achieves significantly lower FKGL than zero-shot GPT-5, indicating better readability, and obtains the highest simplification quality (SARI) among all evaluated models, while remaining broadly competitive on accuracy and semantic similarity. This competitiveness is further improved by an offline medical glossary, which narrows the gap in n-gram overlap and contextual-similarity metrics. These results suggest that collaborative lightweight agents represent a viable approach to improving health literacy in clinical settings. Our code is available at: https://github.com/JackJ3636/LAMP-MedQA"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="johnson-etal-2026-lamp">
<titleInfo>
<title>LAMP-MedQA: A Lightweight Multi-Agent System for Patient-Oriented Medical Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Johnson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meghali</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Crawford</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Welch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jim</namePart>
<namePart type="family">Davies</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tingyan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.Y.S.S.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Diego</namePart>
<namePart type="family">Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ona</namePart>
<namePart type="family">de Gibert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-393-7</identifier>
</relatedItem>
<abstract>Patient health literacy is critical to health outcomes, yet medical discharge summaries remain inaccessible to many patients due to jargon and complex language. Large language models (LLMs) offer a promising means of bridging this gap, but their deployment in resource-constrained hospital environments demands lightweight, privacy-preserving solutions. We evaluate a range of open- and closed-source LLMs on the MeDiSumQA dataset, comprising real patient discharge summaries paired with lay questions and clinician-verified answers, and demonstrate that larger open-source models achieve accuracy and semantic similarity performance comparable to GPT-5. We then introduce LAMP-MedQA, a lightweight multi-agent framework for patient-oriented medical question answering. The framework decomposes the task into two sequential stages: question-relevant evidence extraction and patient-facing answer simplification. Each stage is governed by an automated, metric-driven feedback loop that enables iterative self-correction without human-in-the-loop supervision. Using Qwen2.5-7B-Instruct for generation agents and Phi-3.5-Mini-Instruct for reviewer/verifier agents, it achieves significantly lower FKGL than zero-shot GPT-5, indicating better readability, and obtains the highest simplification quality (SARI) among all evaluated models, while remaining broadly competitive on accuracy and semantic similarity. This competitiveness is further improved by an offline medical glossary, which narrows the gap in n-gram overlap and contextual-similarity metrics. These results suggest that collaborative lightweight agents represent a viable approach to improving health literacy in clinical settings. Our code is available at: https://github.com/JackJ3636/LAMP-MedQA</abstract>
<identifier type="citekey">johnson-etal-2026-lamp</identifier>
<location>
<url>https://aclanthology.org/2026.acl-srw.60/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>663</start>
<end>674</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LAMP-MedQA: A Lightweight Multi-Agent System for Patient-Oriented Medical Question Answering
%A Johnson, Jack A.
%A Banerjee, Meghali
%A Crawford, Joseph
%A Welch, James
%A Davies, Jim
%A Wang, Tingyan
%Y T.Y.S.S., Santosh
%Y Rodriguez, Juan Diego
%Y de Gibert, Ona
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-393-7
%F johnson-etal-2026-lamp
%X Patient health literacy is critical to health outcomes, yet medical discharge summaries remain inaccessible to many patients due to jargon and complex language. Large language models (LLMs) offer a promising means of bridging this gap, but their deployment in resource-constrained hospital environments demands lightweight, privacy-preserving solutions. We evaluate a range of open- and closed-source LLMs on the MeDiSumQA dataset, comprising real patient discharge summaries paired with lay questions and clinician-verified answers, and demonstrate that larger open-source models achieve accuracy and semantic similarity performance comparable to GPT-5. We then introduce LAMP-MedQA, a lightweight multi-agent framework for patient-oriented medical question answering. The framework decomposes the task into two sequential stages: question-relevant evidence extraction and patient-facing answer simplification. Each stage is governed by an automated, metric-driven feedback loop that enables iterative self-correction without human-in-the-loop supervision. Using Qwen2.5-7B-Instruct for generation agents and Phi-3.5-Mini-Instruct for reviewer/verifier agents, it achieves significantly lower FKGL than zero-shot GPT-5, indicating better readability, and obtains the highest simplification quality (SARI) among all evaluated models, while remaining broadly competitive on accuracy and semantic similarity. This competitiveness is further improved by an offline medical glossary, which narrows the gap in n-gram overlap and contextual-similarity metrics. These results suggest that collaborative lightweight agents represent a viable approach to improving health literacy in clinical settings. Our code is available at: https://github.com/JackJ3636/LAMP-MedQA
%U https://aclanthology.org/2026.acl-srw.60/
%P 663-674
Markdown (Informal)
[LAMP-MedQA: A Lightweight Multi-Agent System for Patient-Oriented Medical Question Answering](https://aclanthology.org/2026.acl-srw.60/) (Johnson et al., ACL 2026)
ACL