SzegedAI at ArchEHR-QA 2025: Combining LLMs with traditional methods for grounded question answering

Soma Nagy; Bálint Nyerges; Zsombor Kispéter; Gábor Tóth; András Szlúka; Gábor Kőrösi; Zsolt Szántó; Richárd Farkas

doi:10.18653/v1/2025.bionlp-share.17

SzegedAI at ArchEHR-QA 2025: Combining LLMs with traditional methods for grounded question answering

Soma Nagy, Bálint Nyerges, Zsombor Kispéter, Gábor Tóth, András Szlúka, Gábor Kőrösi, Zsolt Szántó, Richárd Farkas

Correct Metadata for

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>.

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

In this paper, we present the SzegedAI team’s submissions to the ArchEHR-QA 2025 shared task. Our approaches include multiple prompting techniques for large language models (LLMs), sentence similarity methods, and traditional feature engineering. We are aiming to explore both modern and traditional solutions to the task. To combine the strengths of these diverse methods, we employed different ensembling strategies.

Anthology ID:: 2025.bionlp-share.17
Volume:: Proceedings of the 24th Workshop on Biomedical Language Processing (Shared Tasks)
Month:: August
Year:: 2025
Address:: Vienna, Austria
Editors:: Sarvesh Soni, Dina Demner-Fushman
Venues:: BioNLP | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 136–149
Language:
URL:: https://aclanthology.org/2025.bionlp-share.17/
DOI:: 10.18653/v1/2025.bionlp-share.17
Bibkey:
Cite (ACL):: Soma Nagy, Bálint Nyerges, Zsombor Kispéter, Gábor Tóth, András Szlúka, Gábor Kőrösi, Zsolt Szántó, and Richárd Farkas. 2025. SzegedAI at ArchEHR-QA 2025: Combining LLMs with traditional methods for grounded question answering. In Proceedings of the 24th Workshop on Biomedical Language Processing (Shared Tasks), pages 136–149, Vienna, Austria. Association for Computational Linguistics.
Cite (Informal):: SzegedAI at ArchEHR-QA 2025: Combining LLMs with traditional methods for grounded question answering (Nagy et al., BioNLP 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.bionlp-share.17.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{nagy-etal-2025-szegedai,
    title = "{S}zeged{AI} at {A}rch{EHR}-{QA} 2025: Combining {LLM}s with traditional methods for grounded question answering",
    author = {Nagy, Soma  and
      Nyerges, B{\'a}lint  and
      Kisp{\'e}ter, Zsombor  and
      T{\'o}th, G{\'a}bor  and
      Szl{\'u}ka, Andr{\'a}s  and
      K{\H{o}}r{\"o}si, G{\'a}bor  and
      Sz{\'a}nt{\'o}, Zsolt  and
      Farkas, Rich{\'a}rd},
    editor = "Soni, Sarvesh  and
      Demner-Fushman, Dina",
    booktitle = "Proceedings of the 24th Workshop on Biomedical Language Processing (Shared Tasks)",
    month = aug,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.bionlp-share.17/",
    doi = "10.18653/v1/2025.bionlp-share.17",
    pages = "136--149",
    ISBN = "979-8-89176-276-3",
    abstract = "In this paper, we present the SzegedAI team{'}s submissions to the ArchEHR-QA 2025 shared task. Our approaches include multiple prompting techniques for large language models (LLMs), sentence similarity methods, and traditional feature engineering. We are aiming to explore both modern and traditional solutions to the task. To combine the strengths of these diverse methods, we employed different ensembling strategies."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nagy-etal-2025-szegedai">
    <titleInfo>
        <title>SzegedAI at ArchEHR-QA 2025: Combining LLMs with traditional methods for grounded question answering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Soma</namePart>
        <namePart type="family">Nagy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bálint</namePart>
        <namePart type="family">Nyerges</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zsombor</namePart>
        <namePart type="family">Kispéter</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gábor</namePart>
        <namePart type="family">Tóth</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">András</namePart>
        <namePart type="family">Szlúka</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gábor</namePart>
        <namePart type="family">Kőrösi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zsolt</namePart>
        <namePart type="family">Szántó</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Richárd</namePart>
        <namePart type="family">Farkas</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>In this paper, we present the SzegedAI team’s submissions to the ArchEHR-QA 2025 shared task. Our approaches include multiple prompting techniques for large language models (LLMs), sentence similarity methods, and traditional feature engineering. We are aiming to explore both modern and traditional solutions to the task. To combine the strengths of these diverse methods, we employed different ensembling strategies.</abstract>
    <identifier type="citekey">nagy-etal-2025-szegedai</identifier>
    <identifier type="doi">10.18653/v1/2025.bionlp-share.17</identifier>
    <location>
        <url>https://aclanthology.org/2025.bionlp-share.17/</url>
    </location>
    <part>
        <date>2025-08</date>
        <extent unit="page">
            <start>136</start>
            <end>149</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T SzegedAI at ArchEHR-QA 2025: Combining LLMs with traditional methods for grounded question answering
%A Nagy, Soma
%A Nyerges, Bálint
%A Kispéter, Zsombor
%A Tóth, Gábor
%A Szlúka, András
%A Kőrösi, Gábor
%A Szántó, Zsolt
%A Farkas, Richárd
%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 nagy-etal-2025-szegedai
%X In this paper, we present the SzegedAI team’s submissions to the ArchEHR-QA 2025 shared task. Our approaches include multiple prompting techniques for large language models (LLMs), sentence similarity methods, and traditional feature engineering. We are aiming to explore both modern and traditional solutions to the task. To combine the strengths of these diverse methods, we employed different ensembling strategies.
%R 10.18653/v1/2025.bionlp-share.17
%U https://aclanthology.org/2025.bionlp-share.17/
%U https://doi.org/10.18653/v1/2025.bionlp-share.17
%P 136-149

Download as File

Markdown (Informal)

[SzegedAI at ArchEHR-QA 2025: Combining LLMs with traditional methods for grounded question answering](https://aclanthology.org/2025.bionlp-share.17/) (Nagy et al., BioNLP 2025)

SzegedAI at ArchEHR-QA 2025: Combining LLMs with traditional methods for grounded question answering (Nagy et al., BioNLP 2025)

ACL

Soma Nagy, Bálint Nyerges, Zsombor Kispéter, Gábor Tóth, András Szlúka, Gábor Kőrösi, Zsolt Szántó, and Richárd Farkas. 2025. SzegedAI at ArchEHR-QA 2025: Combining LLMs with traditional methods for grounded question answering. In Proceedings of the 24th Workshop on Biomedical Language Processing (Shared Tasks), pages 136–149, Vienna, Austria. Association for Computational Linguistics.