@inproceedings{almannaa-etal-2026-optimed,
title = "{O}pti{M}ed at {A}rch{EHR}-{QA} 2026: {GEPA} Prompt Optimization and Multi-Agent Majority Voting for {EHR}-Grounded Question Answering",
author = "AlMannaa, Feras and
Tseriotou, Talia and
Liakata, Maria",
editor = "Gupta, Deepak and
Thompson, Paul and
Ananiadou, Sophia and
Demner-Fushman, Dina",
booktitle = "Proceedings of the Third Workshop on Patient-Oriented Language Processing ({CL}4{H}ealth) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.cl4health-1.51/",
doi = "10.63317/5gyu3jbn755r",
pages = "539--550",
abstract = "Despite the demonstrated promise of Large Language Models in medical question answering, existing work largely addresses closed-form, exam-style tasks and overlooks complex open-ended questions requiring reasoning over noisy, long clinical documents. In this work, we present our system, OptiMed, submitted to the ArchEHR-QA 2026 shared task on grounded clinical question answering over EHR notes. We combine GEPA, an evolutionary prompt optimization framework, with multi-agent majority voting across five diverse LLMs and a structured clinical abstraction strategy for question interpretation. OptiMed ranked 1st overall among teams completing all four subtasks with an average score of 52.0, achieving top AlignScore in both Question Interpretation and Answer Generation, reflecting strong factual grounding. GEPA optimization proved effective for structured tasks with sufficient development data, but failed to generalize on complex generative tasks under very limited number of supervisions. Multi-agent majority voting consistently lifted performance in evidence-oriented subtasks. Prompt analysis attributes GEPA{'}s gains to role prompting and procedural decomposition and failures to over-specification under limited supervision."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="almannaa-etal-2026-optimed">
<titleInfo>
<title>OptiMed at ArchEHR-QA 2026: GEPA Prompt Optimization and Multi-Agent Majority Voting for EHR-Grounded Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Feras</namePart>
<namePart type="family">AlMannaa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Talia</namePart>
<namePart type="family">Tseriotou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deepak</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Despite the demonstrated promise of Large Language Models in medical question answering, existing work largely addresses closed-form, exam-style tasks and overlooks complex open-ended questions requiring reasoning over noisy, long clinical documents. In this work, we present our system, OptiMed, submitted to the ArchEHR-QA 2026 shared task on grounded clinical question answering over EHR notes. We combine GEPA, an evolutionary prompt optimization framework, with multi-agent majority voting across five diverse LLMs and a structured clinical abstraction strategy for question interpretation. OptiMed ranked 1st overall among teams completing all four subtasks with an average score of 52.0, achieving top AlignScore in both Question Interpretation and Answer Generation, reflecting strong factual grounding. GEPA optimization proved effective for structured tasks with sufficient development data, but failed to generalize on complex generative tasks under very limited number of supervisions. Multi-agent majority voting consistently lifted performance in evidence-oriented subtasks. Prompt analysis attributes GEPA’s gains to role prompting and procedural decomposition and failures to over-specification under limited supervision.</abstract>
<identifier type="citekey">almannaa-etal-2026-optimed</identifier>
<identifier type="doi">10.63317/5gyu3jbn755r</identifier>
<location>
<url>https://aclanthology.org/2026.cl4health-1.51/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>539</start>
<end>550</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OptiMed at ArchEHR-QA 2026: GEPA Prompt Optimization and Multi-Agent Majority Voting for EHR-Grounded Question Answering
%A AlMannaa, Feras
%A Tseriotou, Talia
%A Liakata, Maria
%Y Gupta, Deepak
%Y Thompson, Paul
%Y Ananiadou, Sophia
%Y Demner-Fushman, Dina
%S Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F almannaa-etal-2026-optimed
%X Despite the demonstrated promise of Large Language Models in medical question answering, existing work largely addresses closed-form, exam-style tasks and overlooks complex open-ended questions requiring reasoning over noisy, long clinical documents. In this work, we present our system, OptiMed, submitted to the ArchEHR-QA 2026 shared task on grounded clinical question answering over EHR notes. We combine GEPA, an evolutionary prompt optimization framework, with multi-agent majority voting across five diverse LLMs and a structured clinical abstraction strategy for question interpretation. OptiMed ranked 1st overall among teams completing all four subtasks with an average score of 52.0, achieving top AlignScore in both Question Interpretation and Answer Generation, reflecting strong factual grounding. GEPA optimization proved effective for structured tasks with sufficient development data, but failed to generalize on complex generative tasks under very limited number of supervisions. Multi-agent majority voting consistently lifted performance in evidence-oriented subtasks. Prompt analysis attributes GEPA’s gains to role prompting and procedural decomposition and failures to over-specification under limited supervision.
%R 10.63317/5gyu3jbn755r
%U https://aclanthology.org/2026.cl4health-1.51/
%U https://doi.org/10.63317/5gyu3jbn755r
%P 539-550
Markdown (Informal)
[OptiMed at ArchEHR-QA 2026: GEPA Prompt Optimization and Multi-Agent Majority Voting for EHR-Grounded Question Answering](https://aclanthology.org/2026.cl4health-1.51/) (AlMannaa et al., CL4Health 2026)
ACL