<?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-05226202</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="2026-05-13T12:22:16+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Breaking Boundaries in Citation Parsing: A Comparative Study of Generative LLMs and Traditional Out-of-the-box Citation Parsers</title>
            <author role="aut">
              <persName>
                <forename type="first">Iana</forename>
                <surname>Atanassova</surname>
              </persName>
              <email type="md5">3554b1ef6ade44502182e245e400e92c</email>
              <email type="domain">univ-fcomte.fr</email>
              <ptr type="url" target="https://iana-atanassova.github.io/"/>
              <idno type="idhal" notation="string">iana-atanassova</idno>
              <idno type="idhal" notation="numeric">18491</idno>
              <idno type="halauthorid" notation="string">38892-18491</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-3571-4006</idno>
              <idno type="IDREF">https://www.idref.fr/168283670</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/ABC-5986-2020</idno>
              <idno type="GOOGLE SCHOLAR">ID7dSuIAAAAJ</idno>
              <affiliation ref="#struct-219551"/>
              <affiliation ref="#struct-56663"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Marc</forename>
                <surname>Bertin</surname>
              </persName>
              <email type="md5">ff865b7e99f82ec54b6a33d809fada01</email>
              <email type="domain">gmail.com</email>
              <ptr type="url" target="https://elliadd.univ-fcomte.fr/marc-bertin"/>
              <idno type="idhal" notation="string">marc-bertin</idno>
              <idno type="idhal" notation="numeric">15488</idno>
              <idno type="halauthorid" notation="string">37327-15488</idno>
              <idno type="ARXIV">https://arxiv.org/a/bertin_m_1</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/J-7470-2013</idno>
              <idno type="IDREF">https://www.idref.fr/153705612</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1803-6952</idno>
              <idno type="VIAF">https://viaf.org/viaf/202348879</idno>
              <idno type="ISNI">http://isni.org/isni/0000000357952398</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=8hUgiacAAAAJ&amp;hl=fr</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/J-7470-2013</idno>
              <affiliation ref="#struct-70904"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Iana</forename>
                <surname>Atanassova</surname>
              </persName>
              <email type="md5">34f44368f14ec25073dc3f92c3762e28</email>
              <email type="domain">umlp.fr</email>
            </editor>
            <funder ref="#projanr-51934"/>
            <funder ref="#projanr-55969"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-11-07 20:58:56</date>
              <date type="whenModified">2026-05-13 03:41:59</date>
              <date type="whenReleased">2025-12-24 09:07:38</date>
              <date type="whenProduced">2024-03-24</date>
              <date type="whenEndEmbargoed">2025-11-07</date>
              <ref type="file" target="https://hal.science/hal-05226202v1/document">
                <date notBefore="2025-11-07"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://hal.science/hal-05226202v1/file/BIR_2024_TestingLLM_final.pdf" id="file-5354596-4582617">
                <date notBefore="2025-11-07"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="312161">
                <persName>
                  <forename>Iana</forename>
                  <surname>Atanassova</surname>
                </persName>
                <email type="md5">34f44368f14ec25073dc3f92c3762e28</email>
                <email type="domain">umlp.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05226202</idno>
            <idno type="halUri">https://hal.science/hal-05226202</idno>
            <idno type="halBibtex">atanassova:hal-05226202</idno>
            <idno type="halRefHtml">&lt;i&gt;Proceedings of the 14th International Workshop on Bibliometric-enhanced Information Retrieval, and 1st Workshop on Information Retrieval for Understudied Users co-located with 45th European Conference on Information Retrieval (ECIR 2024)&lt;/i&gt;, Mar 2024, Glascow, United Kingdom. pp.38-52</idno>
            <idno type="halRef">Proceedings of the 14th International Workshop on Bibliometric-enhanced Information Retrieval, and 1st Workshop on Information Retrieval for Understudied Users co-located with 45th European Conference on Information Retrieval (ECIR 2024), Mar 2024, Glascow, United Kingdom. pp.38-52</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal<ref corresp="#file-5354596-4582617"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="SHS">Sciences de l'Homme et de la Société</idno>
            <idno type="stamp" n="UNIV-LYON3">Université Jean Moulin - Lyon III</idno>
            <idno type="stamp" n="UNIV-LYON1">Université Claude Bernard - Lyon I</idno>
            <idno type="stamp" n="UNIV-LYON2">Université Lumière Lyon 2</idno>
            <idno type="stamp" n="ELICO" corresp="UNIV-LYON1">Equipe de recherche de Lyon en sciences de l'information et de la communication</idno>
            <idno type="stamp" n="LYON2">Université Lyon2</idno>
            <idno type="stamp" n="UDL">UDL</idno>
            <idno type="stamp" n="UNIV-LYON">Université de Lyon</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="ISTEX">Infrastructure de services pour la fouille de textes</idno>
            <idno type="stamp" n="HAL-LYON-2-NOUVELLE-VERSION">Nouvelle version portail </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="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Breaking Boundaries in Citation Parsing: A Comparative Study of Generative LLMs and Traditional Out-of-the-box Citation Parsers</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Iana</forename>
                    <surname>Atanassova</surname>
                  </persName>
                  <email type="md5">3554b1ef6ade44502182e245e400e92c</email>
                  <email type="domain">univ-fcomte.fr</email>
                  <ptr type="url" target="https://iana-atanassova.github.io/"/>
                  <idno type="idhal" notation="string">iana-atanassova</idno>
                  <idno type="idhal" notation="numeric">18491</idno>
                  <idno type="halauthorid" notation="string">38892-18491</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-3571-4006</idno>
                  <idno type="IDREF">https://www.idref.fr/168283670</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/ABC-5986-2020</idno>
                  <idno type="GOOGLE SCHOLAR">ID7dSuIAAAAJ</idno>
                  <affiliation ref="#struct-219551"/>
                  <affiliation ref="#struct-56663"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Marc</forename>
                    <surname>Bertin</surname>
                  </persName>
                  <email type="md5">ff865b7e99f82ec54b6a33d809fada01</email>
                  <email type="domain">gmail.com</email>
                  <ptr type="url" target="https://elliadd.univ-fcomte.fr/marc-bertin"/>
                  <idno type="idhal" notation="string">marc-bertin</idno>
                  <idno type="idhal" notation="numeric">15488</idno>
                  <idno type="halauthorid" notation="string">37327-15488</idno>
                  <idno type="ARXIV">https://arxiv.org/a/bertin_m_1</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/J-7470-2013</idno>
                  <idno type="IDREF">https://www.idref.fr/153705612</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1803-6952</idno>
                  <idno type="VIAF">https://viaf.org/viaf/202348879</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000357952398</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=8hUgiacAAAAJ&amp;hl=fr</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/J-7470-2013</idno>
                  <affiliation ref="#struct-70904"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">CEUR Workshop Proceedings</title>
                <meeting>
                  <title>Proceedings of the 14th International Workshop on Bibliometric-enhanced Information Retrieval, and 1st Workshop on Information Retrieval for Understudied Users co-located with 45th European Conference on Information Retrieval (ECIR 2024)</title>
                  <date type="start">2024-03-24</date>
                  <date type="end">2024-03-24</date>
                  <settlement>Glascow</settlement>
                  <country key="GB">United Kingdom</country>
                </meeting>
                <imprint>
                  <biblScope unit="volume">3989</biblScope>
                  <biblScope unit="pp">38-52</biblScope>
                  <date type="datePub">2025-07-02</date>
                </imprint>
              </monogr>
              <ref target="https://ceur-ws.org/Vol-3989/paper-04.pdf" type="seeAlso"/>
              <ref type="publisher">https://sites.google.com/view/bir-ws/bir-2024</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">References</term>
                <term xml:lang="en">Llama</term>
                <term xml:lang="en">CERMINE</term>
                <term xml:lang="en">Neural ParsCit</term>
                <term xml:lang="en">ChatGPT</term>
                <term xml:lang="en">Generative LLMs Citation string parsing Reference parsing BibT E X ChatGPT Neural ParsCit CERMINE Llama References</term>
                <term xml:lang="en">Reference parsing</term>
                <term xml:lang="en">Citation string parsing</term>
                <term xml:lang="en">Generative LLMs</term>
                <term xml:lang="en">BibTEX</term>
              </keywords>
              <classCode scheme="halDomain" n="shs.info">Humanities and Social Sciences/Library and information sciences</classCode>
              <classCode scheme="halDomain" n="info.info-ir">Computer Science [cs]/Information Retrieval [cs.IR]</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 task of citation string parsing has been the focus of many efforts. Traditional tools explicitly designedto parse bibliographic information, such as Bilbo, Grobid, and Parscit, have long been established in theacademic landscape. Recently, with the emergence of general conversational LLMs (Large LanguageModels) such as OpenAI’s ChatGPT and Llama, an interesting question arises: can such language models,originally developed for natural language understanding (NLU), be employed to efficiently processbibliographies, and how would their performance for this task compare to that of dedicated bibliographicparsing tools? In this article, we propose an experiment to measure the ability of LLMs to analysecitation strings in different citation styles. We use a synthetic dataset with 12 different citation styles.We evaluate the output of two generative LLMs, ChatGPT 3.5 and Llama 2 7B, and two out-of-the-boxcitation parsers, CERMINE and Neural ParsCit. The results show that the LLMs tend to outperform thecitation parsers for all citation styles and labels.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-219551" status="VALID">
          <idno type="IdRef">031477232</idno>
          <idno type="RNSR">199114522D</idno>
          <orgName>Centre de recherches interdisciplinaires et transculturelles - UFC (UR 3224)</orgName>
          <orgName type="acronym">CRIT</orgName>
          <desc>
            <address>
              <addrLine>UFR SLHS 32 rue Mégevand 25030 Besançon Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-fcomte.fr/pages/fr/menu1/recherche/la-recherche-a-l-ufc/ea-3224---crit-18229-8133.html</ref>
          </desc>
          <listRelation>
            <relation name="UR 3224" active="#struct-458810" type="direct"/>
            <relation active="#struct-426438" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-56663" status="VALID">
          <idno type="IdRef">03442945X</idno>
          <idno type="ISNI">0000000119314817</idno>
          <idno type="ROR">https://ror.org/055khg266</idno>
          <idno type="Wikidata">Q1665127</idno>
          <orgName>Institut universitaire de France</orgName>
          <orgName type="acronym">IUF</orgName>
          <desc>
            <address>
              <addrLine>Maison des Universités 103 Boulevard Saint-Michel 75005 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://iuf.amue.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301855" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-70904" status="VALID">
          <idno type="IdRef">134928474</idno>
          <idno type="RNSR">200715391D</idno>
          <idno type="ROR">https://ror.org/04y24xj84</idno>
          <orgName>Equipe de recherche de Lyon en sciences de l'information et de la communication</orgName>
          <orgName type="acronym">ELICO</orgName>
          <desc>
            <address>
              <addrLine>Université Lumière Lyon 2 - Département ICOM5 avenue Pierre-Mendes-France 69676 Bron</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.elico-recherche.eu/</ref>
          </desc>
          <listRelation>
            <relation name="EA4147" active="#struct-33804" type="direct"/>
            <relation active="#struct-43938" type="direct"/>
            <relation active="#struct-301088" type="indirect"/>
            <relation active="#struct-59112" type="direct"/>
            <relation active="#struct-118744" type="direct"/>
            <relation active="#struct-194495" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-458810" status="VALID">
          <idno type="IdRef">026403188</idno>
          <idno type="ISNI">0000000121883779</idno>
          <idno type="ROR">https://ror.org/03pcc9z86</idno>
          <orgName>Université Marie et Louis Pasteur</orgName>
          <orgName type="acronym">UMLP</orgName>
          <desc>
            <address>
              <addrLine>1 rue Goudimel25030 Besançon cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.umlp.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-426438" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-426438" status="VALID">
          <idno type="IdRef">200716271</idno>
          <idno type="ISNI">0000 0004 4910 6615</idno>
          <idno type="ROR">https://ror.org/02dn7x778</idno>
          <orgName>Université Bourgogne Franche-Comté [COMUE]</orgName>
          <orgName type="acronym">UBFC</orgName>
          <date type="start">2015-04-01</date>
          <date type="end">2024-12-31</date>
          <desc>
            <address>
              <addrLine>32, avenue de l’observatoire25000 BESANCON</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ubfc.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-301855" status="VALID">
          <orgName>Ministère de l'Education nationale, de l’Enseignement supérieur et de la Recherche</orgName>
          <orgName type="acronym">M.E.N.E.S.R.</orgName>
          <desc>
            <address>
              <addrLine>1 rue Descartes - 75231 Paris cedex 05</addrLine>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-33804" status="VALID">
          <idno type="IdRef">02640334X</idno>
          <idno type="ISNI">0000 0001 2188 0906</idno>
          <idno type="ROR">https://ror.org/03rth4p18</idno>
          <idno type="Wikidata">Q4041</idno>
          <orgName>Université Lumière - Lyon 2</orgName>
          <orgName type="acronym">UL2</orgName>
          <desc>
            <address>
              <addrLine>86, rue Pasteur - 69007 Lyon</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lyon2.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-43938" status="VALID">
          <idno type="ROR">https://ror.org/059qr5h87</idno>
          <orgName>École nationale supérieure des sciences de l'information et des bibliothèques</orgName>
          <orgName type="acronym">ENSSIB</orgName>
          <desc>
            <address>
              <addrLine>17-21, avenue du 11 Novembre 1918 - 69623 Villeurbanne Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.enssib.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301088" status="VALID">
          <idno type="ROR">https://ror.org/01rk35k63</idno>
          <orgName>Université de Lyon</orgName>
          <desc>
            <address>
              <addrLine>92 rue Pasteur - CS 30122, 69361 Lyon Cedex 07</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-lyon.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-59112" status="VALID">
          <idno type="IdRef">028888537</idno>
          <idno type="ROR">https://ror.org/02h3vcz70</idno>
          <orgName>Sciences Po Lyon - Institut d'études politiques de Lyon</orgName>
          <orgName type="acronym">IEP Lyon</orgName>
          <desc>
            <address>
              <addrLine>14 avenue Berthelot - 69365 Lyon cedex 07</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.sciencespo-lyon.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-118744" status="VALID">
          <idno type="IdRef">026404494</idno>
          <idno type="ISNI">0000000121920883</idno>
          <idno type="ROR">https://ror.org/05b5c0584</idno>
          <orgName>Université Jean Moulin - Lyon 3</orgName>
          <orgName type="acronym">UJML</orgName>
          <date type="start">1973-07-26</date>
          <desc>
            <address>
              <addrLine>6 cours Albert Thomas - 69008 Lyon</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lyon3.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-194495" status="VALID">
          <idno type="IdRef">026402823</idno>
          <idno type="ISNI">0000000121686185</idno>
          <idno type="ROR">https://ror.org/029brtt94</idno>
          <orgName>Université Claude Bernard Lyon 1</orgName>
          <orgName type="acronym">UCBL</orgName>
          <desc>
            <address>
              <addrLine>43, boulevard du 11 novembre 1918, 69622 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lyon1.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-51934" status="VALID">
          <idno type="anr">ANR-20-CE38-0003</idno>
          <orgName>TheoScit</orgName>
          <desc>Etude des contextes de citation pour une construction d'indicateurs relationnels sémantiques</desc>
          <date type="start">2020</date>
        </org>
        <org type="anrProject" xml:id="projanr-55969" status="VALID">
          <idno type="anr">ANR-21-CE38-0003</idno>
          <orgName>InSciM</orgName>
          <desc>Modélisation de l'incertitude en science</desc>
          <date type="start">2021</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>