<?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-05091439</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="2026-05-14T20:06:12+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Alignment of Schema-Only and Instance-Only Data Sources Using Large Language Models</title>
            <author role="aut">
              <persName>
                <forename type="first">Nour</forename>
                <forename type="middle">Elhouda</forename>
                <surname>Kired</surname>
              </persName>
              <idno type="idhal" notation="numeric">1418372</idno>
              <idno type="halauthorid" notation="string">3554116-1418372</idno>
              <idno type="ORCID">https://orcid.org/0009-0009-0610-6280</idno>
              <affiliation ref="#struct-1612872"/>
              <affiliation ref="#struct-81148"/>
              <affiliation ref="#struct-116256"/>
              <affiliation ref="#struct-1612881"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Franck</forename>
                <surname>Ravat</surname>
              </persName>
              <email type="md5">e57861390e1847a5a0bb1af8e79ed391</email>
              <email type="domain">irit.fr</email>
              <idno type="idhal" notation="string">franck-ravat</idno>
              <idno type="idhal" notation="numeric">735308</idno>
              <idno type="halauthorid" notation="string">8576-735308</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-4820-841X</idno>
              <idno type="IDREF">https://www.idref.fr/127663711</idno>
              <affiliation ref="#struct-1612881"/>
              <affiliation ref="#struct-81148"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Jiefu</forename>
                <surname>Song</surname>
              </persName>
              <email type="md5">20765259bf572d91ccd943236ef308c7</email>
              <email type="domain">irit.fr</email>
              <idno type="idhal" notation="string">jiefu-song</idno>
              <idno type="idhal" notation="numeric">735992</idno>
              <idno type="halauthorid" notation="string">25297-735992</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-2066-7051</idno>
              <affiliation ref="#struct-1612881"/>
              <affiliation ref="#struct-81148"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Olivier</forename>
                <surname>Teste</surname>
              </persName>
              <email type="md5">c88c9779b8539d22b8a6920e97c8244a</email>
              <email type="domain">irit.fr</email>
              <idno type="idhal" notation="string">olivier-teste</idno>
              <idno type="idhal" notation="numeric">117280</idno>
              <idno type="halauthorid" notation="string">51109-117280</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/C-6850-2012</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-0338-9886</idno>
              <idno type="ISNI">http://isni.org/isni/0000000009251819</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=cbPGlwUAAAAJ&amp;hl=fr</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=cbPGlwUAAAAJ&amp;hl=fr</idno>
              <idno type="IDREF">https://www.idref.fr/076013286</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/C-6850-2012</idno>
              <affiliation ref="#struct-301231"/>
              <affiliation ref="#struct-1612881"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Nour Elhouda</forename>
                <surname>KIRED</surname>
              </persName>
              <email type="md5">23afa1e811154b7927f8965ec3bd5ae5</email>
              <email type="domain">irit.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-05-31 17:44:11</date>
              <date type="whenModified">2026-03-24 03:01:01</date>
              <date type="whenReleased">2025-06-05 10:15:30</date>
              <date type="whenProduced">2025-05-12</date>
              <date type="whenEndEmbargoed">2025-12-01</date>
              <ref type="file" target="https://univ-tlse2.hal.science/hal-05091439v1/document">
                <date notBefore="2025-12-01"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://univ-tlse2.hal.science/hal-05091439v1/file/RCIS_2025_paper_62.pdf" id="file-5091439-4403303">
                <date notBefore="2025-12-01"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1553811">
                <persName>
                  <forename>Nour Elhouda</forename>
                  <surname>KIRED</surname>
                </persName>
                <email type="md5">23afa1e811154b7927f8965ec3bd5ae5</email>
                <email type="domain">irit.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05091439</idno>
            <idno type="halUri">https://univ-tlse2.hal.science/hal-05091439</idno>
            <idno type="halBibtex">kired:hal-05091439</idno>
            <idno type="halRefHtml">&lt;i&gt;Lecture Notes in Business Information Processing&lt;/i&gt;, 2025, pp.67 - 85. &lt;a target="_blank" href="https://dx.doi.org/10.1007/978-3-031-92471-2_5"&gt;&amp;#x27E8;10.1007/978-3-031-92471-2_5&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Lecture Notes in Business Information Processing, 2025, pp.67 - 85. &amp;#x27E8;10.1007/978-3-031-92471-2_5&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-5091439-4403303"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-TLSE2">Université Toulouse 2</idno>
            <idno type="stamp" n="UNIV-TLSE3">Université de Toulouse</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UT1-CAPITOLE">Université Toulouse 1 Capitole</idno>
            <idno type="stamp" n="IRIT">IRIT - Institut de Recherche en Informatique de Toulouse</idno>
            <idno type="stamp" n="IRIT-SIG" corresp="IRIT">Systèmes d’Informations Généralisées</idno>
            <idno type="stamp" n="IUT-BLAGNAC" corresp="UNIV-TLSE2">IUT Blagnac</idno>
            <idno type="stamp" n="IRIT-GD" corresp="IRIT">Gestion des Données</idno>
            <idno type="stamp" n="TOULOUSE-INP">Toulouse - INP</idno>
            <idno type="stamp" n="UNIV-UT3">Université Toulouse 3</idno>
            <idno type="stamp" n="UT3-INP">Université de Toulouse / Toulouse INP</idno>
            <idno type="stamp" n="UT3-TOULOUSEINP">Université de Toulouse / Toulouse INP</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Alignment of Schema-Only and Instance-Only Data Sources Using Large Language Models</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Nour</forename>
                    <forename type="middle">Elhouda</forename>
                    <surname>Kired</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">1418372</idno>
                  <idno type="halauthorid" notation="string">3554116-1418372</idno>
                  <idno type="ORCID">https://orcid.org/0009-0009-0610-6280</idno>
                  <affiliation ref="#struct-1612872"/>
                  <affiliation ref="#struct-81148"/>
                  <affiliation ref="#struct-116256"/>
                  <affiliation ref="#struct-1612881"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Franck</forename>
                    <surname>Ravat</surname>
                  </persName>
                  <email type="md5">e57861390e1847a5a0bb1af8e79ed391</email>
                  <email type="domain">irit.fr</email>
                  <idno type="idhal" notation="string">franck-ravat</idno>
                  <idno type="idhal" notation="numeric">735308</idno>
                  <idno type="halauthorid" notation="string">8576-735308</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-4820-841X</idno>
                  <idno type="IDREF">https://www.idref.fr/127663711</idno>
                  <affiliation ref="#struct-1612881"/>
                  <affiliation ref="#struct-81148"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Jiefu</forename>
                    <surname>Song</surname>
                  </persName>
                  <email type="md5">20765259bf572d91ccd943236ef308c7</email>
                  <email type="domain">irit.fr</email>
                  <idno type="idhal" notation="string">jiefu-song</idno>
                  <idno type="idhal" notation="numeric">735992</idno>
                  <idno type="halauthorid" notation="string">25297-735992</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-2066-7051</idno>
                  <affiliation ref="#struct-1612881"/>
                  <affiliation ref="#struct-81148"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Olivier</forename>
                    <surname>Teste</surname>
                  </persName>
                  <email type="md5">c88c9779b8539d22b8a6920e97c8244a</email>
                  <email type="domain">irit.fr</email>
                  <idno type="idhal" notation="string">olivier-teste</idno>
                  <idno type="idhal" notation="numeric">117280</idno>
                  <idno type="halauthorid" notation="string">51109-117280</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/C-6850-2012</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-0338-9886</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000009251819</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=cbPGlwUAAAAJ&amp;hl=fr</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=cbPGlwUAAAAJ&amp;hl=fr</idno>
                  <idno type="IDREF">https://www.idref.fr/076013286</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/C-6850-2012</idno>
                  <affiliation ref="#struct-301231"/>
                  <affiliation ref="#struct-1612881"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">114168</idno>
                <idno type="issn">1865-1348</idno>
                <idno type="eissn">1865-1356</idno>
                <title level="j">Lecture Notes in Business Information Processing</title>
                <imprint>
                  <publisher>Springer</publisher>
                  <biblScope unit="pp">67 - 85</biblScope>
                  <date type="datePub">2025-05-12</date>
                  <date type="dateEpub">2025-05-15</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1007/978-3-031-92471-2_5</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Data matching</term>
                <term xml:lang="en">Disparate Data Source Structures</term>
                <term xml:lang="en">Auxiliary Information Generation</term>
                <term xml:lang="en">Matcher Combination</term>
              </keywords>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>&lt;div&gt;&lt;p&gt;Data matching is a persistent challenge in heterogeneous data integration. Traditional data matching methods, relying on schemabased, instance-based, or hybrid approaches, often fall short when aligning disparate data from schema-only with instance-only sources. To address this problem of aligning disparate sources, we present an innovative data matching framework that enables the matching of one data source, where only schema-related information is available, with another data source, where only instance-related information is available. The strength of our framework lies in its ability to combine outputs from multiple Schema-Instances matchers, generating auxiliary information to enhance the alignment between disparate data structures. Our framework is validated using the Valentine Benchmark through extensive experiments. These findings underscore the potential of our approach to advance the integration of diverse data sources.&lt;/p&gt;&lt;/div&gt;</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-1612872" status="VALID">
          <idno type="IdRef">030947448</idno>
          <idno type="ISNI">0000000121927225</idno>
          <idno type="RNSR">199511949P</idno>
          <idno type="ROR">https://ror.org/01rx4qw44</idno>
          <orgName>Institut de recherche en informatique de Toulouse</orgName>
          <orgName type="acronym">IRIT</orgName>
          <date type="start">2025-01-01</date>
          <desc>
            <address>
              <addrLine>118 Route de Narbonne, F-31062 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.irit.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-81148" type="direct"/>
            <relation name="443875" active="#struct-443875" type="indirect"/>
            <relation active="#struct-116256" type="direct"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation name="UMR5505" active="#struct-441569" type="direct"/>
            <relation active="#struct-448187" type="direct"/>
            <relation active="#struct-1574795" type="direct"/>
            <relation active="#struct-1612865" type="direct"/>
            <relation name="FED4171" active="#struct-1574795" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-81148" status="VALID">
          <idno type="IdRef">026404354</idno>
          <idno type="ISNI">0000000121902837</idno>
          <idno type="ROR">https://ror.org/0443n9e75</idno>
          <orgName>Université Toulouse Capitole</orgName>
          <orgName type="acronym">UT Capitole</orgName>
          <date type="start">1970-01-01</date>
          <desc>
            <address>
              <addrLine>2 rue du Doyen-Gabriel-Marty - 31042 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ut-capitole.fr/</ref>
          </desc>
          <listRelation>
            <relation name="443875" active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-116256" status="VALID">
          <idno type="IdRef">026403994</idno>
          <idno type="ROR">https://ror.org/04ezk3x31</idno>
          <orgName>Université Toulouse - Jean Jaurès</orgName>
          <orgName type="acronym">UT2J</orgName>
          <date type="start">1971-01-01</date>
          <desc>
            <address>
              <addrLine>5 allées Antonio Machado - 31058 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-tlse2.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-1612881" status="VALID">
          <orgName>Systèmes d’Informations Généralisées</orgName>
          <orgName type="acronym">IRIT-SIG</orgName>
          <date type="start">2025-01-01</date>
          <desc>
            <address>
              <addrLine>IRIT118 Route de Narbonne31062 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.irit.fr/departement/gestion-des-donnees/equipe-sig/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1612872" type="direct"/>
            <relation active="#struct-81148" type="indirect"/>
            <relation name="443875" active="#struct-443875" type="indirect"/>
            <relation active="#struct-116256" type="indirect"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation name="UMR5505" active="#struct-441569" type="indirect"/>
            <relation active="#struct-448187" type="indirect"/>
            <relation active="#struct-1574795" type="indirect"/>
            <relation active="#struct-1612865" type="indirect"/>
            <relation name="FED4171" active="#struct-1574795" type="indirect"/>
          </listRelation>
        </org>
        <org type="regrouplaboratory" xml:id="struct-301231" status="VALID">
          <orgName>IUT Toulouse 2 Blagnac</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-116256" type="direct"/>
            <relation active="#struct-443875" type="indirect"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-443875" status="VALID">
          <idno type="ROR">https://ror.org/017tgbk05</idno>
          <orgName>Communauté d'universités et établissements de Toulouse</orgName>
          <orgName type="acronym">Comue de Toulouse</orgName>
          <desc>
            <address>
              <addrLine>41 Allée Jules Guesde, 31000 Toulouse</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-toulouse.fr/</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-448187" status="VALID">
          <idno type="IdRef">026388820</idno>
          <idno type="ISNI">0000000121766169</idno>
          <idno type="ROR">https://ror.org/033p9g875</idno>
          <orgName>Institut National Polytechnique (Toulouse)</orgName>
          <orgName type="acronym">Toulouse INP</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.inp-toulouse.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-1574795" status="VALID">
          <orgName>Université de Toulouse</orgName>
          <orgName type="acronym">EPE UT</orgName>
          <date type="start">2025-01-01</date>
          <desc>
            <address>
              <addrLine>118 toute de Narbonne, 31062 Toulouse cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-tlse3.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="regrouplaboratory" xml:id="struct-1612865" status="VALID">
          <orgName>Toulouse Mind &amp; Brain Institut</orgName>
          <orgName type="acronym">TMBI</orgName>
          <date type="start">2025-01-01</date>
          <desc>
            <address>
              <addrLine>CHU Purpan, Pavillon Baudot, 31059 Toulouse cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.tmbi.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-116256" type="direct"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation name="FED4171" active="#struct-1574795" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>