Beyond One-Size-Fits-All: Multi-Agent Refinement Framework for Persona-Based Biomedical Summarization

Rohan Charudatt Salvi; Chirag Chawla; Md. Shad Akhtar; Shweta Yadav

doi:10.63317/22uei8f8k9za

Beyond One-Size-Fits-All: Multi-Agent Refinement Framework for Persona-Based Biomedical Summarization

Rohan Charudatt Salvi, Chirag Chawla, Md. Shad Akhtar, Shweta Yadav

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the external publication .)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Lay summarization aims to make biomedical research accessible to non-experts, but most approaches assume a uniform audience, overlooking variation in medical literacy and information needs. We present MAPS (Multi-Agent Persona-based Summarization), a framework that generates persona-specific summaries through iterative cross-agent feedback. Human evaluation shows MAPS improves quality over single-agent baselines, while automatic metrics fail to capture these gains. LLM-based judges also exhibit limited sensitivity, assigning inflated scores and misdetecting errors. These findings highlight the need for improved evaluation methods for persona-based summarization.

Anthology ID:: 2026.cl4health-1.28
Volume:: Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026
Month:: May
Year:: 2026
Address:: Palma, Mallorca (Spain)
Editors:: Deepak Gupta, Paul Thompson, Sophia Ananiadou, Dina Demner-Fushman
Venues:: CL4Health | WS
SIG:
Publisher:: ELRA Language Resources Association (ELRA)
Note:
Pages:: 320–332
Language:
External URL:: https://lrec.elra.info/lrec2026-ws-cl4health-28
DOI:: 10.63317/22uei8f8k9za
Bibkey:
Cite (ACL):: Rohan Charudatt Salvi, Chirag Chawla, Md. Shad Akhtar, and Shweta Yadav. 2026. Beyond One-Size-Fits-All: Multi-Agent Refinement Framework for Persona-Based Biomedical Summarization. In Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026, pages 320–332, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):: Beyond One-Size-Fits-All: Multi-Agent Refinement Framework for Persona-Based Biomedical Summarization (Salvi et al., CL4Health 2026)
Copy Citation:

External Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{salvi-etal-2026-beyond,
    title = "Beyond One-Size-Fits-All: Multi-Agent Refinement Framework for Persona-Based Biomedical Summarization",
    author = "Salvi, Rohan Charudatt  and
      Chawla, Chirag  and
      Akhtar, Md. Shad  and
      Yadav, Shweta",
    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-1.28/",
    doi = "10.63317/22uei8f8k9za",
    pages = "320--332",
    abstract = "Lay summarization aims to make biomedical research accessible to non-experts, but most approaches assume a uniform audience, overlooking variation in medical literacy and information needs. We present MAPS (Multi-Agent Persona-based Summarization), a framework that generates persona-specific summaries through iterative cross-agent feedback. Human evaluation shows MAPS improves quality over single-agent baselines, while automatic metrics fail to capture these gains. LLM-based judges also exhibit limited sensitivity, assigning inflated scores and misdetecting errors. These findings highlight the need for improved evaluation methods for persona-based summarization."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="salvi-etal-2026-beyond">
    <titleInfo>
        <title>Beyond One-Size-Fits-All: Multi-Agent Refinement Framework for Persona-Based Biomedical Summarization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rohan</namePart>
        <namePart type="given">Charudatt</namePart>
        <namePart type="family">Salvi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chirag</namePart>
        <namePart type="family">Chawla</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Md.</namePart>
        <namePart type="given">Shad</namePart>
        <namePart type="family">Akhtar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shweta</namePart>
        <namePart type="family">Yadav</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>Lay summarization aims to make biomedical research accessible to non-experts, but most approaches assume a uniform audience, overlooking variation in medical literacy and information needs. We present MAPS (Multi-Agent Persona-based Summarization), a framework that generates persona-specific summaries through iterative cross-agent feedback. Human evaluation shows MAPS improves quality over single-agent baselines, while automatic metrics fail to capture these gains. LLM-based judges also exhibit limited sensitivity, assigning inflated scores and misdetecting errors. These findings highlight the need for improved evaluation methods for persona-based summarization.</abstract>
    <identifier type="citekey">salvi-etal-2026-beyond</identifier>
    <identifier type="doi">10.63317/22uei8f8k9za</identifier>
    <location>
        <url>https://aclanthology.org/2026.cl4health-1.28/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>320</start>
            <end>332</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Beyond One-Size-Fits-All: Multi-Agent Refinement Framework for Persona-Based Biomedical Summarization
%A Salvi, Rohan Charudatt
%A Chawla, Chirag
%A Akhtar, Md. Shad
%A Yadav, Shweta
%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 salvi-etal-2026-beyond
%X Lay summarization aims to make biomedical research accessible to non-experts, but most approaches assume a uniform audience, overlooking variation in medical literacy and information needs. We present MAPS (Multi-Agent Persona-based Summarization), a framework that generates persona-specific summaries through iterative cross-agent feedback. Human evaluation shows MAPS improves quality over single-agent baselines, while automatic metrics fail to capture these gains. LLM-based judges also exhibit limited sensitivity, assigning inflated scores and misdetecting errors. These findings highlight the need for improved evaluation methods for persona-based summarization.
%R 10.63317/22uei8f8k9za
%U https://aclanthology.org/2026.cl4health-1.28/
%U https://doi.org/10.63317/22uei8f8k9za
%P 320-332

Download as File

Markdown (Informal)

[Beyond One-Size-Fits-All: Multi-Agent Refinement Framework for Persona-Based Biomedical Summarization](https://aclanthology.org/2026.cl4health-1.28/) (Salvi et al., CL4Health 2026)

Beyond One-Size-Fits-All: Multi-Agent Refinement Framework for Persona-Based Biomedical Summarization (Salvi et al., CL4Health 2026)

ACL

Rohan Charudatt Salvi, Chirag Chawla, Md. Shad Akhtar, and Shweta Yadav. 2026. Beyond One-Size-Fits-All: Multi-Agent Refinement Framework for Persona-Based Biomedical Summarization. In Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026, pages 320–332, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).