<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shields-menard-etal-2025-utsa">
    <titleInfo>
        <title>UTSA-NLP at ArchEHR-QA 2025: Improving EHR Question Answering via Self-Consistency Prompting</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sara</namePart>
        <namePart type="family">Shields-Menard</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zach</namePart>
        <namePart type="family">Reimers</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Joshua</namePart>
        <namePart type="family">Gardner</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="family">Perry</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anthony</namePart>
        <namePart type="family">Rios</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 24th Workshop on Biomedical Language Processing (Shared Tasks)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Sarvesh</namePart>
            <namePart type="family">Soni</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">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-276-3</identifier>
    </relatedItem>
    <abstract>We describe our system for the ArchEHR-QA Shared Task on answering clinical questions using electronic health records (EHRs). Our approach uses large language models in two steps: first, to find sentences in the EHR relevant to a clinician’s question, and second, to generate a short, citation-supported response based on those sentences. We use few-shot prompting, self-consistency, and thresholding to improve the sentence classification step to decide which sentences are essential. We compare several models and find that a smaller 8B model performs better than a larger 70B model for identifying relevant information. Our results show that accurate sentence selection is critical for generating high-quality responses and that self-consistency with thresholding helps make these decisions more reliable.</abstract>
    <identifier type="citekey">shields-menard-etal-2025-utsa</identifier>
    <identifier type="doi">10.18653/v1/2025.bionlp-share.10</identifier>
    <location>
        <url>https://aclanthology.org/2025.bionlp-share.10/</url>
    </location>
    <part>
        <date>2025-08</date>
        <extent unit="page">
            <start>81</start>
            <end>90</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T UTSA-NLP at ArchEHR-QA 2025: Improving EHR Question Answering via Self-Consistency Prompting
%A Shields-Menard, Sara
%A Reimers, Zach
%A Gardner, Joshua
%A Perry, David
%A Rios, Anthony
%Y Soni, Sarvesh
%Y Demner-Fushman, Dina
%S Proceedings of the 24th Workshop on Biomedical Language Processing (Shared Tasks)
%D 2025
%8 August
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-276-3
%F shields-menard-etal-2025-utsa
%X We describe our system for the ArchEHR-QA Shared Task on answering clinical questions using electronic health records (EHRs). Our approach uses large language models in two steps: first, to find sentences in the EHR relevant to a clinician’s question, and second, to generate a short, citation-supported response based on those sentences. We use few-shot prompting, self-consistency, and thresholding to improve the sentence classification step to decide which sentences are essential. We compare several models and find that a smaller 8B model performs better than a larger 70B model for identifying relevant information. Our results show that accurate sentence selection is critical for generating high-quality responses and that self-consistency with thresholding helps make these decisions more reliable.
%R 10.18653/v1/2025.bionlp-share.10
%U https://aclanthology.org/2025.bionlp-share.10/
%U https://doi.org/10.18653/v1/2025.bionlp-share.10
%P 81-90

Markdown (Informal)

[UTSA-NLP at ArchEHR-QA 2025: Improving EHR Question Answering via Self-Consistency Prompting](https://aclanthology.org/2025.bionlp-share.10/) (Shields-Menard et al., BioNLP 2025)

• UTSA-NLP at ArchEHR-QA 2025: Improving EHR Question Answering via Self-Consistency Prompting (Shields-Menard et al., BioNLP 2025)

ACL

• Sara Shields-Menard, Zach Reimers, Joshua Gardner, David Perry, and Anthony Rios. 2025. UTSA-NLP at ArchEHR-QA 2025: Improving EHR Question Answering via Self-Consistency Prompting. In Proceedings of the 24th Workshop on Biomedical Language Processing (Shared Tasks), pages 81–90, Vienna, Austria. Association for Computational Linguistics.