<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-04470883</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-17T04:16:01+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">A Zero-shot and Few-shot Study of Instruction-Finetuned Large Language Models Applied to Clinical and Biomedical Tasks</title>
            <author role="aut">
              <persName>
                <forename type="first">Yanis</forename>
                <surname>Labrak</surname>
              </persName>
              <email type="md5">8c4b5d82482a85dc0e9975b264973ae9</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">yanis-labrak</idno>
              <idno type="idhal" notation="numeric">750624</idno>
              <idno type="halauthorid" notation="string">2522822-750624</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1072-3862</idno>
              <affiliation ref="#struct-100376"/>
              <affiliation ref="#struct-1148517"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Mickaël</forename>
                <surname>Rouvier</surname>
              </persName>
              <email type="md5">e6a0714032faea385562d6f6ae15b4f3</email>
              <email type="domain">univ-avignon.fr</email>
              <idno type="idhal" notation="string">mickael-rouvier</idno>
              <idno type="idhal" notation="numeric">982551</idno>
              <idno type="halauthorid" notation="string">1029325-982551</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-3541-3385</idno>
              <affiliation ref="#struct-100376"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Richard</forename>
                <surname>Dufour</surname>
              </persName>
              <email type="md5">9b1e2d4b46fdead01a210134637ca965</email>
              <email type="domain">univ-nantes.fr</email>
              <idno type="idhal" notation="string">richard-dufour</idno>
              <idno type="idhal" notation="numeric">178348</idno>
              <idno type="halauthorid" notation="string">18347-178348</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1203-9108</idno>
              <affiliation ref="#struct-1088575"/>
              <affiliation ref="#struct-100376"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Yanis</forename>
                <surname>Labrak</surname>
              </persName>
              <email type="md5">8c4b5d82482a85dc0e9975b264973ae9</email>
              <email type="domain">gmail.com</email>
            </editor>
            <funder ref="#projanr-109432"/>
            <funder>Zenidoc</funder>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2024-02-21 13:38:19</date>
              <date type="whenModified">2026-02-04 03:08:57</date>
              <date type="whenReleased">2024-02-21 13:54:49</date>
              <date type="whenProduced">2024-05-20</date>
              <date type="whenEndEmbargoed">2024-02-21</date>
              <ref type="file" target="https://hal.science/hal-04470883v1/document">
                <date notBefore="2024-02-21"/>
              </ref>
              <ref type="file" n="1" target="https://hal.science/hal-04470883v1/file/A%20Zero-shot%20and%20Few-shot%20Study%20of%20Instruction-Finetuned%20Large%20Language%20Models%20Applied%20to%20Clinical%20and%20Biomedical%20Tasks%20%281%29.pdf" id="file-4470883-3878552">
                <date notBefore="2024-02-21"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1105687">
                <persName>
                  <forename>Yanis</forename>
                  <surname>Labrak</surname>
                </persName>
                <email type="md5">8c4b5d82482a85dc0e9975b264973ae9</email>
                <email type="domain">gmail.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04470883</idno>
            <idno type="halUri">https://hal.science/hal-04470883</idno>
            <idno type="halBibtex">labrak:hal-04470883</idno>
            <idno type="halRefHtml">&lt;i&gt;Fourteenth Language Resources and Evaluation Conference (LREC-COLING 2024)&lt;/i&gt;, Nicoletta Calzolari; Min-Yen Kan, May 2024, Torino, Italy</idno>
            <idno type="halRef">Fourteenth Language Resources and Evaluation Conference (LREC-COLING 2024), Nicoletta Calzolari; Min-Yen Kan, May 2024, Torino, Italy</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal<ref corresp="#file-4470883-3878552"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-AVIGNON">Université d'Avignon</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="EC-NANTES">Ecole Centrale de Nantes</idno>
            <idno type="stamp" n="UNAM">l'unam - université nantes angers le mans</idno>
            <idno type="stamp" n="LS2N">Laboratoire des Sciences du Numérique de Nantes</idno>
            <idno type="stamp" n="LS2N-TALN" corresp="LS2N">LS2N - équipe TALN ( Traitement Automatique du Langage Naturel )</idno>
            <idno type="stamp" n="LIA" corresp="UNIV-AVIGNON">Laboratoire Informatique d'Avignon</idno>
            <idno type="stamp" n="INSTITUTS-TELECOM">composantes instituts telecom </idno>
            <idno type="stamp" n="TALN-RECITAL">Conférences TALN RECITAL</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="NANTES-UNIVERSITE">Nantes Université</idno>
            <idno type="stamp" n="NANTES-UNIV">Nantes Université</idno>
            <idno type="stamp" n="JEP-TALN-RECITAL2024" corresp="TALN-RECITAL">CONFÉRENCE JEP TALN RECITAL 2024</idno>
            <idno type="stamp" n="ANR-IA-23" corresp="ANR-IA">ANR-IA-23</idno>
            <idno type="stamp" n="ANR-IA">ANR-IA</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">A Zero-shot and Few-shot Study of Instruction-Finetuned Large Language Models Applied to Clinical and Biomedical Tasks</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Yanis</forename>
                    <surname>Labrak</surname>
                  </persName>
                  <email type="md5">8c4b5d82482a85dc0e9975b264973ae9</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">yanis-labrak</idno>
                  <idno type="idhal" notation="numeric">750624</idno>
                  <idno type="halauthorid" notation="string">2522822-750624</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1072-3862</idno>
                  <affiliation ref="#struct-100376"/>
                  <affiliation ref="#struct-1148517"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Mickaël</forename>
                    <surname>Rouvier</surname>
                  </persName>
                  <email type="md5">e6a0714032faea385562d6f6ae15b4f3</email>
                  <email type="domain">univ-avignon.fr</email>
                  <idno type="idhal" notation="string">mickael-rouvier</idno>
                  <idno type="idhal" notation="numeric">982551</idno>
                  <idno type="halauthorid" notation="string">1029325-982551</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-3541-3385</idno>
                  <affiliation ref="#struct-100376"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Richard</forename>
                    <surname>Dufour</surname>
                  </persName>
                  <email type="md5">9b1e2d4b46fdead01a210134637ca965</email>
                  <email type="domain">univ-nantes.fr</email>
                  <idno type="idhal" notation="string">richard-dufour</idno>
                  <idno type="idhal" notation="numeric">178348</idno>
                  <idno type="halauthorid" notation="string">18347-178348</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1203-9108</idno>
                  <affiliation ref="#struct-1088575"/>
                  <affiliation ref="#struct-100376"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>Fourteenth Language Resources and Evaluation Conference (LREC-COLING 2024)</title>
                  <date type="start">2024-05-20</date>
                  <date type="end">2024-05-25</date>
                  <settlement>Torino</settlement>
                  <country key="IT">Italy</country>
                </meeting>
                <respStmt>
                  <resp>conferenceOrganizer</resp>
                  <name>Nicoletta Calzolari</name>
                  <name>Min-Yen Kan</name>
                </respStmt>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">BERT</term>
                <term xml:lang="en">Transformers</term>
                <term xml:lang="en">Large Language Models</term>
                <term xml:lang="en">Clinical</term>
                <term xml:lang="en">Biomedical</term>
                <term xml:lang="en">Medical domain</term>
                <term xml:lang="en">Benchmarking</term>
                <term xml:lang="en">NLP evaluation</term>
              </keywords>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halDomain" n="info.info-cl">Computer Science [cs]/Computation and Language [cs.CL]</classCode>
              <classCode scheme="halDomain" n="info.info-lg">Computer Science [cs]/Machine Learning [cs.LG]</classCode>
              <classCode scheme="halDomain" n="info.info-tt">Computer Science [cs]/Document and Text Processing</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>The recent emergence of Large Language Models (LLMs) has enabled significant advances in the field of Natural Language Processing (NLP). While these new models have demonstrated superior performance on various tasks, their application and potential are still underexplored, both in terms of the diversity of tasks they can handle and their domain of application. In this context, we evaluate four state-of-the-art instruction-tuned LLMs (ChatGPT, Flan-T5 UL2, Tk-Instruct, and Alpaca) on a set of 13 real-world clinical and biomedical NLP tasks in English, including named-entity recognition (NER), question-answering (QA), relation extraction (RE), and more. Our overall results show that these evaluated LLMs approach the performance of state-of-the-art models in zero- and few-shot scenarios for most tasks, particularly excelling in the QA task, even though they have never encountered examples from these tasks before. However, we also observe that the classification and RE tasks fall short of the performance achievable with specifically trained models designed for the medical field, such as PubMedBERT. Finally, we note that no single LLM outperforms all others across all studied tasks, with some models proving more suitable for certain tasks than others.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-100376" status="VALID">
          <orgName>Laboratoire Informatique d'Avignon</orgName>
          <orgName type="acronym">LIA</orgName>
          <desc>
            <address>
              <addrLine>339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://lia.univ-avignon.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-195507" type="direct"/>
            <relation active="#struct-302221" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-1148517" status="INCOMING">
          <orgName>Zenidoc</orgName>
          <desc>
            <address>
              <addrLine>1 Avenue Marius Pinatel, 13380 Plan-de-Cuques</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://zenidoc.fr/</ref>
          </desc>
        </org>
        <org type="researchteam" xml:id="struct-1088575" status="VALID">
          <orgName>Traitement Automatique du Langage Naturel</orgName>
          <orgName type="acronym">LS2N - équipe TALN</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-1088564" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation name="UMR6004" active="#struct-441569" type="indirect"/>
            <relation active="#struct-481355" type="indirect"/>
            <relation active="#struct-302102" type="indirect"/>
            <relation active="#struct-1086798" type="indirect"/>
            <relation active="#struct-1083366" type="indirect"/>
            <relation active="#struct-1088543" type="indirect"/>
            <relation active="#struct-1083400" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-195507" status="VALID">
          <idno type="ROR">https://ror.org/00mfpxb84</idno>
          <orgName>Avignon Université</orgName>
          <orgName type="acronym">AU</orgName>
          <desc>
            <address>
              <addrLine>74 rue Louis Pasteur - 84 029 Avignon cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-avignon.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-302221" status="VALID">
          <orgName>Centre d'Enseignement et de Recherche en Informatique - CERI</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-1088564" status="VALID">
          <idno type="IdRef">203637585</idno>
          <idno type="RNSR">201722241F</idno>
          <idno type="ROR">https://ror.org/02snf8m58</idno>
          <orgName>Laboratoire des Sciences du Numérique de Nantes</orgName>
          <orgName type="acronym">LS2N</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <addrLine>Nantes Université – faculté des Sciences et Techniques (FST)2 Chemin de la HoussinièreBP 92208, 44322 Nantes Cedex 3</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.ls2n.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
            <relation name="UMR6004" active="#struct-441569" type="direct"/>
            <relation active="#struct-481355" type="direct"/>
            <relation active="#struct-302102" type="indirect"/>
            <relation active="#struct-1086798" type="direct"/>
            <relation active="#struct-1083366" type="indirect"/>
            <relation active="#struct-1088543" type="direct"/>
            <relation active="#struct-1083400" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300009" status="VALID">
          <idno type="ROR">https://ror.org/02kvxyf05</idno>
          <orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
          <orgName type="acronym">Inria</orgName>
          <desc>
            <address>
              <addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/en/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-481355" status="VALID">
          <idno type="IdRef">202743233</idno>
          <idno type="ROR">https://ror.org/030hj3061</idno>
          <orgName>IMT Atlantique</orgName>
          <orgName type="acronym">IMT Atlantique</orgName>
          <date type="start">2017-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Brest : Technopôle Brest-Iroise CS 8381829238 BREST Cedex 3 -Campus Nantes : 4, rue Alfred Kastler- La chantrerie 44300 NANTES -Campus Rennes :  2 Rue de la Châtaigneraie, 35510 CESSON SEVIGNE</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.imt-atlantique.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-302102" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-302102" status="VALID">
          <idno type="IdRef">192427156</idno>
          <idno type="ISNI">000000012202567X</idno>
          <idno type="ROR">https://ror.org/025vp2923</idno>
          <idno type="Wikidata">Q27962533</idno>
          <orgName>Institut Mines-Télécom [Paris]</orgName>
          <orgName type="acronym">IMT</orgName>
          <date type="start">2012-03-01</date>
          <desc>
            <address>
              <addrLine>19 Place Marguerite Perey, 91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.imt.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-1086798" status="VALID">
          <idno type="IdRef">03063525X</idno>
          <idno type="ISNI">0000000122039289</idno>
          <idno type="ROR">https://ror.org/03nh7d505</idno>
          <orgName>NANTES UNIVERSITÉ - École Centrale de Nantes</orgName>
          <orgName type="acronym">Nantes Univ - ECN</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <addrLine>1 rue de la Noë - BP 92101 - 44321 Nantes cedex 3</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ec-nantes.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1083366" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-1083366" status="VALID">
          <idno type="IdRef">258086599</idno>
          <idno type="ROR">https://ror.org/03gnr7b55</idno>
          <orgName>Nantes Université</orgName>
          <orgName type="acronym">Nantes Univ</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="regrouplaboratory" xml:id="struct-1088543" status="VALID">
          <orgName>Nantes université - UFR des Sciences et des Techniques</orgName>
          <orgName type="acronym">Nantes univ -  UFR ST</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <addrLine>2, rue de la Houssinière - BP 92208 - 44322 Nantes cedex 3</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.sciences-techniques.univ-nantes.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1083400" type="direct"/>
            <relation active="#struct-1083366" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-1083400" status="VALID">
          <orgName>Nantes Université - pôle Sciences et technologie</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://nouvelleuniversite.univ-nantes.fr/les-poles</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1083366" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-109432" status="VALID">
          <idno type="anr">ANR-23-IAS1-0005</idno>
          <orgName>MALADES</orgName>
          <desc>Grands modèles de langue adaptables et souverains pour le domaine médical français</desc>
          <date type="start">2023</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>