Retrieval-Augmented Simplification of Sectioned Biomedical Abstracts

Pascal Mathas; Jan Bakker; Jaap Kamps

Retrieval-Augmented Simplification of Sectioned Biomedical Abstracts

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 PDF.)

Authors concatenated from the text boxes above:

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

Abstract

Cochrane systematic reviews pair each technical abstract with a plain-language summary (PLS), but most biomedical papers lack a PLS. We propose a retrieval-augmented generation (RAG) pipeline that generates Cochrane PLS from biomedical abstracts. The pipeline exploits the section-level alignment of the Cochrane-sections dataset in two ways. First, it provides the LLM with abstract-PLS section pairs from topically related reviews, giving more granular in-context examples than whole abstract-PLS pairs. Second, each retrieved PLS section is split into its rephrased and inserted sentences, showing the LLM both the rephrasing and the insertion behavior it should reproduce. Our pipeline outperforms a non-RAG LLM and three RAG ablations on the Cochrane-sections test set, with the same gain trend across three different LLM families.

Anthology ID:: 2026.findings-emnlp.1513
Volume:: Findings of the Association for Computational Linguistics: EMNLP 2026
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Hung-Yi Lee, Sunipa Dev, Jessy Li, Desmond Elliott
Venue:: Findings
SIG:: SIGDAT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 32209–32219
Language:
URL:: https://aclanthology.org/2026.findings-emnlp.1513/
DOI:
Bibkey:
Cite (ACL):: Pascal Mathas, Jan Bakker, and Jaap Kamps. 2026. Retrieval-Augmented Simplification of Sectioned Biomedical Abstracts. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 32209–32219, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: Retrieval-Augmented Simplification of Sectioned Biomedical Abstracts (Mathas et al., Findings 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.findings-emnlp.1513.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{mathas-etal-2026-retrieval,
    title = "Retrieval-Augmented Simplification of Sectioned Biomedical Abstracts",
    author = "Mathas, Pascal  and
      Bakker, Jan  and
      Kamps, Jaap",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.1513/",
    pages = "32209--32219",
    ISBN = "979-8-89176-462-0",
    abstract = "Cochrane systematic reviews pair each technical abstract with a plain-language summary (PLS), but most biomedical papers lack a PLS. We propose a retrieval-augmented generation (RAG) pipeline that generates Cochrane PLS from biomedical abstracts. The pipeline exploits the section-level alignment of the Cochrane-sections dataset in two ways. First, it provides the LLM with abstract-PLS section pairs from topically related reviews, giving more granular in-context examples than whole abstract-PLS pairs. Second, each retrieved PLS section is split into its rephrased and inserted sentences, showing the LLM both the rephrasing and the insertion behavior it should reproduce. Our pipeline outperforms a non-RAG LLM and three RAG ablations on the Cochrane-sections test set, with the same gain trend across three different LLM families."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mathas-etal-2026-retrieval">
    <titleInfo>
        <title>Retrieval-Augmented Simplification of Sectioned Biomedical Abstracts</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pascal</namePart>
        <namePart type="family">Mathas</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jan</namePart>
        <namePart type="family">Bakker</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jaap</namePart>
        <namePart type="family">Kamps</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Cochrane systematic reviews pair each technical abstract with a plain-language summary (PLS), but most biomedical papers lack a PLS. We propose a retrieval-augmented generation (RAG) pipeline that generates Cochrane PLS from biomedical abstracts. The pipeline exploits the section-level alignment of the Cochrane-sections dataset in two ways. First, it provides the LLM with abstract-PLS section pairs from topically related reviews, giving more granular in-context examples than whole abstract-PLS pairs. Second, each retrieved PLS section is split into its rephrased and inserted sentences, showing the LLM both the rephrasing and the insertion behavior it should reproduce. Our pipeline outperforms a non-RAG LLM and three RAG ablations on the Cochrane-sections test set, with the same gain trend across three different LLM families.</abstract>
    <identifier type="citekey">mathas-etal-2026-retrieval</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1513/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>32209</start>
            <end>32219</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Retrieval-Augmented Simplification of Sectioned Biomedical Abstracts
%A Mathas, Pascal
%A Bakker, Jan
%A Kamps, Jaap
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F mathas-etal-2026-retrieval
%X Cochrane systematic reviews pair each technical abstract with a plain-language summary (PLS), but most biomedical papers lack a PLS. We propose a retrieval-augmented generation (RAG) pipeline that generates Cochrane PLS from biomedical abstracts. The pipeline exploits the section-level alignment of the Cochrane-sections dataset in two ways. First, it provides the LLM with abstract-PLS section pairs from topically related reviews, giving more granular in-context examples than whole abstract-PLS pairs. Second, each retrieved PLS section is split into its rephrased and inserted sentences, showing the LLM both the rephrasing and the insertion behavior it should reproduce. Our pipeline outperforms a non-RAG LLM and three RAG ablations on the Cochrane-sections test set, with the same gain trend across three different LLM families.
%U https://aclanthology.org/2026.findings-emnlp.1513/
%P 32209-32219

Download as File

Markdown (Informal)

[Retrieval-Augmented Simplification of Sectioned Biomedical Abstracts](https://aclanthology.org/2026.findings-emnlp.1513/) (Mathas et al., Findings 2026)

Retrieval-Augmented Simplification of Sectioned Biomedical Abstracts (Mathas et al., Findings 2026)

ACL

Pascal Mathas, Jan Bakker, and Jaap Kamps. 2026. Retrieval-Augmented Simplification of Sectioned Biomedical Abstracts. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 32209–32219, Budapest, Hungary. Association for Computational Linguistics.