<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chiewhawan-etal-2026-lamar">
    <titleInfo>
        <title>LAMAR at MedExACT 2026: Agreement-Driven Large Language Model Ensembles for Clinical Decision Extraction from Discharge Summaries</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Monrada</namePart>
        <namePart type="family">Chiewhawan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Keetawan</namePart>
        <namePart type="family">Limaroon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Titipat</namePart>
        <namePart type="family">Achakulvisut</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 BioNLP 2026 (Shared Tasks)</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">Dina</namePart>
            <namePart type="family">Demner-Fushman</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, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-435-4</identifier>
    </relatedItem>
    <abstract>This paper presents an ensemble of Qwen3.5-4B language models for extracting medical decisions from discharge summaries in the MedDec dataset. The models were trained to annotate discharge summaries with inline XML-like tags. Three different training strategies were used including dynamic fine-tuning, reinforcement learning, and pseudo-label augmentation. By combining predictions based on inter-model agreement, the system improved performance across evaluation metrics, achieving an overall F1 of 0.5942 and ranking second on the test leaderboard. The results also showed stable performance across demographic groups, suggesting fairness for underrepresented populations.</abstract>
    <identifier type="citekey">chiewhawan-etal-2026-lamar</identifier>
    <location>
        <url>https://aclanthology.org/2026.bionlp-2.25/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>179</start>
            <end>190</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T LAMAR at MedExACT 2026: Agreement-Driven Large Language Model Ensembles for Clinical Decision Extraction from Discharge Summaries
%A Chiewhawan, Monrada
%A Limaroon, Keetawan
%A Achakulvisut, Titipat
%Y Gupta, Deepak
%Y Demner-Fushman, Dina
%S Proceedings of the BioNLP 2026 (Shared Tasks)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-435-4
%F chiewhawan-etal-2026-lamar
%X This paper presents an ensemble of Qwen3.5-4B language models for extracting medical decisions from discharge summaries in the MedDec dataset. The models were trained to annotate discharge summaries with inline XML-like tags. Three different training strategies were used including dynamic fine-tuning, reinforcement learning, and pseudo-label augmentation. By combining predictions based on inter-model agreement, the system improved performance across evaluation metrics, achieving an overall F1 of 0.5942 and ranking second on the test leaderboard. The results also showed stable performance across demographic groups, suggesting fairness for underrepresented populations.
%U https://aclanthology.org/2026.bionlp-2.25/
%P 179-190

Markdown (Informal)

[LAMAR at MedExACT 2026: Agreement-Driven Large Language Model Ensembles for Clinical Decision Extraction from Discharge Summaries](https://aclanthology.org/2026.bionlp-2.25/) (Chiewhawan et al., BioNLP 2026)

• LAMAR at MedExACT 2026: Agreement-Driven Large Language Model Ensembles for Clinical Decision Extraction from Discharge Summaries (Chiewhawan et al., BioNLP 2026)

ACL

• Monrada Chiewhawan, Keetawan Limaroon, and Titipat Achakulvisut. 2026. LAMAR at MedExACT 2026: Agreement-Driven Large Language Model Ensembles for Clinical Decision Extraction from Discharge Summaries. In Proceedings of the BioNLP 2026 (Shared Tasks), pages 179–190, San Diego, California, USA. Association for Computational Linguistics.