<?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-05226285</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="2026-05-24T03:47:56+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">EuroBERT: Scaling Multilingual Encoders for European Languages</title>
            <author role="aut">
              <persName>
                <forename type="first">Nicolas</forename>
                <surname>Boizard</surname>
              </persName>
              <idno type="halauthorid">3149172-0</idno>
              <affiliation ref="#struct-1042590"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Hippolyte</forename>
                <surname>Gisserot-Boukhlef</surname>
              </persName>
              <idno type="halauthorid">3149163-0</idno>
              <affiliation ref="#struct-1042590"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Duarte</forename>
                <forename type="middle">M.</forename>
                <surname>Alves</surname>
              </persName>
              <email type="md5">df92c3695d427d95d211b19e9e41f4d8</email>
              <email type="domain">tecnico.ulisboa.pt</email>
              <idno type="idhal" notation="numeric">1574634</idno>
              <idno type="halauthorid" notation="string">3734591-1574634</idno>
              <affiliation ref="#struct-501124"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">André</forename>
                <forename type="middle">F T</forename>
                <surname>Martins</surname>
              </persName>
              <email type="md5">94c89f31ab5eee80c95b5bbf6688c05f</email>
              <email type="domain">unbabel.com</email>
              <idno type="idhal" notation="numeric">1074793</idno>
              <idno type="halauthorid" notation="string">2001599-1074793</idno>
              <affiliation ref="#struct-501124"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Ayoub</forename>
                <surname>Hammal</surname>
              </persName>
              <email type="md5">203faa762d16e60ba057d6de9b813e7a</email>
              <email type="domain">lisn.fr</email>
              <idno type="idhal" notation="numeric">1487521</idno>
              <idno type="halauthorid" notation="string">3364299-1487521</idno>
              <affiliation ref="#struct-419361"/>
              <affiliation ref="#struct-1065372"/>
              <affiliation ref="#struct-1061259"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Caio</forename>
                <surname>Corro</surname>
              </persName>
              <email type="md5">7368d0ace4509011716321f1ce35eec5</email>
              <email type="domain">lisn.upsaclay.fr</email>
              <idno type="idhal" notation="string">caiocorro</idno>
              <idno type="idhal" notation="numeric">740403</idno>
              <idno type="halauthorid" notation="string">50215-740403</idno>
              <idno type="ARXIV">https://arxiv.org/a/corro_c_1</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-7443-4109</idno>
              <idno type="IDREF">https://www.idref.fr/242971059</idno>
              <idno type="VIAF">https://viaf.org/viaf/1950159234156503370909</idno>
              <affiliation ref="#struct-1092628"/>
              <affiliation ref="#struct-117606"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Céline</forename>
                <surname>Hudelot</surname>
              </persName>
              <email type="md5">f47c8e3cb17a2bf7d43f2c152bb86885</email>
              <email type="domain">centralesupelec.fr</email>
              <idno type="idhal" notation="string">celine-hudelot</idno>
              <idno type="idhal" notation="numeric">20877</idno>
              <idno type="halauthorid" notation="string">30850-20877</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-3849-4133</idno>
              <idno type="ARXIV">https://arxiv.org/a/hudelot_c_1</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=gFlAh6MAAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/113366744</idno>
              <affiliation ref="#struct-1042590"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Emmanuel</forename>
                <surname>Malherbe</surname>
              </persName>
              <idno type="halauthorid">1086774-0</idno>
              <affiliation ref="#struct-1063427"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Etienne</forename>
                <surname>Malaboeuf</surname>
              </persName>
              <email type="md5">21848ee3fac215cff56a1742c7720354</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">etiennemlb</idno>
              <idno type="idhal" notation="numeric">1556964</idno>
              <idno type="halauthorid" notation="string">3611965-1556964</idno>
              <idno type="ORCID">https://orcid.org/0009-0007-3320-1406</idno>
              <affiliation ref="#struct-300898"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Fanny</forename>
                <surname>Jourdan</surname>
              </persName>
              <email type="md5">6cda2a815dcec43eeed4e2ff051466ca</email>
              <email type="domain">irt-saintexupery.com</email>
              <idno type="idhal" notation="string">fanny-jourdan</idno>
              <idno type="idhal" notation="numeric">1225483</idno>
              <idno type="halauthorid" notation="string">2719582-1225483</idno>
              <idno type="ARXIV">https://arxiv.org/a/jourdan_f_1</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=ntU8A30AAAAJ</idno>
              <affiliation ref="#struct-417643"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Gabriel</forename>
                <surname>Hautreux</surname>
              </persName>
              <idno type="halauthorid">980135-0</idno>
              <affiliation ref="#struct-300898"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">João</forename>
                <surname>Alves</surname>
              </persName>
              <idno type="halauthorid">402006-0</idno>
              <affiliation ref="#struct-566893"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Kevin</forename>
                <surname>El-Haddad</surname>
              </persName>
              <idno type="halauthorid">3734592-0</idno>
              <affiliation ref="#struct-29983"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Manuel</forename>
                <surname>Faysse</surname>
              </persName>
              <email type="md5">faba2cb4c50d2f16cc1a96f8f4a8ab56</email>
              <email type="domain">centralesupelec.fr</email>
              <idno type="idhal" notation="string">manuel-faysse</idno>
              <idno type="idhal" notation="numeric">1511892</idno>
              <idno type="halauthorid" notation="string">3148323-1511892</idno>
              <idno type="GOOGLE SCHOLAR">ew4xsR4AAAAJ</idno>
              <idno type="ARXIV">https://arxiv.org/a/faysse_m_1</idno>
              <idno type="ORCID">https://orcid.org/0009-0009-3424-5800</idno>
              <affiliation ref="#struct-1225281"/>
              <affiliation ref="#struct-411575"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Maxime</forename>
                <surname>Peyrard</surname>
              </persName>
              <email type="md5">d214b11d3f38faedb4b8c16401892a36</email>
              <email type="domain">univ-grenoble-alpes.fr</email>
              <idno type="idhal" notation="string">maxime-peyrard</idno>
              <idno type="idhal" notation="numeric">1423948</idno>
              <idno type="halauthorid" notation="string">2297120-1423948</idno>
              <affiliation ref="#struct-1043313"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Nuno</forename>
                <forename type="middle">M</forename>
                <surname>Guerreiro</surname>
              </persName>
              <idno type="halauthorid">3149320-0</idno>
              <affiliation ref="#struct-1042590"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Patrick</forename>
                <surname>Fernandes</surname>
              </persName>
              <idno type="halauthorid">1547426-0</idno>
              <affiliation ref="#struct-501124"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Ricardo</forename>
                <surname>Rei</surname>
              </persName>
              <idno type="halauthorid">3149158-0</idno>
              <affiliation ref="#struct-566893"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Pierre</forename>
                <surname>Colombo</surname>
              </persName>
              <email type="md5">e2d5dac3d92757ed48e37e126a3464a3</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">pierre-colombo</idno>
              <idno type="idhal" notation="numeric">743646</idno>
              <idno type="halauthorid" notation="string">1007669-743646</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=yPoMt8gAAAAJ&amp;hl=fr</idno>
              <idno type="IDREF">https://www.idref.fr/258975059</idno>
              <affiliation ref="#struct-1042590"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Maxime</forename>
                <surname>Peyrard</surname>
              </persName>
              <email type="md5">d214b11d3f38faedb4b8c16401892a36</email>
              <email type="domain">univ-grenoble-alpes.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-08-27 14:26:32</date>
              <date type="whenModified">2026-04-30 13:41:07</date>
              <date type="whenReleased">2025-09-11 14:27:26</date>
              <date type="whenProduced">2025-10-07</date>
              <date type="whenEndEmbargoed">2025-08-27</date>
              <ref type="file" target="https://hal.science/hal-05226285v1/document">
                <date notBefore="2025-08-27"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-05226285v1/file/2503.05500v2.pdf" id="file-5226285-4511129">
                <date notBefore="2025-08-27"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/2503.05500"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1529305">
                <persName>
                  <forename>Maxime</forename>
                  <surname>Peyrard</surname>
                </persName>
                <email type="md5">d214b11d3f38faedb4b8c16401892a36</email>
                <email type="domain">univ-grenoble-alpes.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05226285</idno>
            <idno type="halUri">https://hal.science/hal-05226285</idno>
            <idno type="halBibtex">boizard:hal-05226285</idno>
            <idno type="halRefHtml">&lt;i&gt;COLM 2025 - Second Conference on Language Modeling&lt;/i&gt;, Oct 2025, Montreal, Canada. pp.1-28</idno>
            <idno type="halRef">COLM 2025 - Second Conference on Language Modeling, Oct 2025, Montreal, Canada. pp.1-28</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-5226285-4511129"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="ENSMP" corresp="PARISTECH">MINES ParisTech</idno>
            <idno type="stamp" n="UNIV-RENNES1">Université de Rennes 1</idno>
            <idno type="stamp" n="UGA">HAL Grenoble Alpes</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="UNIV-UBS">Université de Bretagne Sud</idno>
            <idno type="stamp" n="INSA-RENNES">Institut National des Sciences Appliquées de Rennes</idno>
            <idno type="stamp" n="INPG">Institut polytechnique de Grenoble</idno>
            <idno type="stamp" n="INRIA-RENNES">INRIA Rennes - Bretagne Atlantique</idno>
            <idno type="stamp" n="IRISA">Irisa</idno>
            <idno type="stamp" n="LIG">Laboratoire d'Informatique de Grenoble</idno>
            <idno type="stamp" n="IRISA_SET">IRISA_SET</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="LIG_TDCGE_GETALP" corresp="LIG_TDCGE">GETALP</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="IRISA-INSA-R" corresp="IRISA">Institut de Recherche en Informatique et Systèmes Aléatoires - Composante INSA Rennes</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="MICS">Mathématiques et Informatique pour la Complexité et les Systèmes</idno>
            <idno type="stamp" n="UR1-HAL">Publications labos UR1 dans HAL-Rennes 1</idno>
            <idno type="stamp" n="PSL">Université Paris sciences et lettres</idno>
            <idno type="stamp" n="UR1-MATH-STIC">UR1 - publications Maths-STIC</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="UR1-UFR-ISTIC">UFR ISTIC Informatique et électronique</idno>
            <idno type="stamp" n="IRT_SAINT-EXUPERY">IRT Saint Exupéry - Institut de Recherche Technologique</idno>
            <idno type="stamp" n="TEST-UR-CSS">TEST Université de Rennes CSS</idno>
            <idno type="stamp" n="UNIV-RENNES">Université de Rennes</idno>
            <idno type="stamp" n="INRIA-RENGRE">INRIA-RENGRE</idno>
            <idno type="stamp" n="INSA-GROUPE">Groupe INSA</idno>
            <idno type="stamp" n="ENSMP-PSL" corresp="PSL">MINES ParisTech - École nationale supérieure des mines de Paris - PSL</idno>
            <idno type="stamp" n="UNIVERSITE-PARIS-SACLAY" corresp="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="UGA-EPE">Université Grenoble Alpes [2020-*]</idno>
            <idno type="stamp" n="UR1-MATH-NUM">Pôle UnivRennes - Mathématiques - Numérique </idno>
            <idno type="stamp" n="LISN">Laboratoire Interdisciplinaire des Sciences du Numérique</idno>
            <idno type="stamp" n="GS-COMPUTER-SCIENCE">Graduate School Computer Science</idno>
            <idno type="stamp" n="CYBERSCHOOL">CyberSchool - Ecole universitaire de recherche en Cybersécurité</idno>
            <idno type="stamp" n="HUB-IA">Hub Intelligence Artificielle de CentraleSupélec</idno>
            <idno type="stamp" n="LISN-STL">Sciences et Technologies des Langues</idno>
            <idno type="stamp" n="TEST-UGA">TEST-UGA</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">EuroBERT: Scaling Multilingual Encoders for European Languages</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Nicolas</forename>
                    <surname>Boizard</surname>
                  </persName>
                  <idno type="halauthorid">3149172-0</idno>
                  <affiliation ref="#struct-1042590"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Hippolyte</forename>
                    <surname>Gisserot-Boukhlef</surname>
                  </persName>
                  <idno type="halauthorid">3149163-0</idno>
                  <affiliation ref="#struct-1042590"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Duarte</forename>
                    <forename type="middle">M.</forename>
                    <surname>Alves</surname>
                  </persName>
                  <email type="md5">df92c3695d427d95d211b19e9e41f4d8</email>
                  <email type="domain">tecnico.ulisboa.pt</email>
                  <idno type="idhal" notation="numeric">1574634</idno>
                  <idno type="halauthorid" notation="string">3734591-1574634</idno>
                  <affiliation ref="#struct-501124"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">André</forename>
                    <forename type="middle">F T</forename>
                    <surname>Martins</surname>
                  </persName>
                  <email type="md5">94c89f31ab5eee80c95b5bbf6688c05f</email>
                  <email type="domain">unbabel.com</email>
                  <idno type="idhal" notation="numeric">1074793</idno>
                  <idno type="halauthorid" notation="string">2001599-1074793</idno>
                  <affiliation ref="#struct-501124"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Ayoub</forename>
                    <surname>Hammal</surname>
                  </persName>
                  <email type="md5">203faa762d16e60ba057d6de9b813e7a</email>
                  <email type="domain">lisn.fr</email>
                  <idno type="idhal" notation="numeric">1487521</idno>
                  <idno type="halauthorid" notation="string">3364299-1487521</idno>
                  <affiliation ref="#struct-419361"/>
                  <affiliation ref="#struct-1065372"/>
                  <affiliation ref="#struct-1061259"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Caio</forename>
                    <surname>Corro</surname>
                  </persName>
                  <email type="md5">7368d0ace4509011716321f1ce35eec5</email>
                  <email type="domain">lisn.upsaclay.fr</email>
                  <idno type="idhal" notation="string">caiocorro</idno>
                  <idno type="idhal" notation="numeric">740403</idno>
                  <idno type="halauthorid" notation="string">50215-740403</idno>
                  <idno type="ARXIV">https://arxiv.org/a/corro_c_1</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-7443-4109</idno>
                  <idno type="IDREF">https://www.idref.fr/242971059</idno>
                  <idno type="VIAF">https://viaf.org/viaf/1950159234156503370909</idno>
                  <affiliation ref="#struct-1092628"/>
                  <affiliation ref="#struct-117606"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Céline</forename>
                    <surname>Hudelot</surname>
                  </persName>
                  <email type="md5">f47c8e3cb17a2bf7d43f2c152bb86885</email>
                  <email type="domain">centralesupelec.fr</email>
                  <idno type="idhal" notation="string">celine-hudelot</idno>
                  <idno type="idhal" notation="numeric">20877</idno>
                  <idno type="halauthorid" notation="string">30850-20877</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-3849-4133</idno>
                  <idno type="ARXIV">https://arxiv.org/a/hudelot_c_1</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=gFlAh6MAAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/113366744</idno>
                  <affiliation ref="#struct-1042590"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Emmanuel</forename>
                    <surname>Malherbe</surname>
                  </persName>
                  <idno type="halauthorid">1086774-0</idno>
                  <affiliation ref="#struct-1063427"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Etienne</forename>
                    <surname>Malaboeuf</surname>
                  </persName>
                  <email type="md5">21848ee3fac215cff56a1742c7720354</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">etiennemlb</idno>
                  <idno type="idhal" notation="numeric">1556964</idno>
                  <idno type="halauthorid" notation="string">3611965-1556964</idno>
                  <idno type="ORCID">https://orcid.org/0009-0007-3320-1406</idno>
                  <affiliation ref="#struct-300898"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Fanny</forename>
                    <surname>Jourdan</surname>
                  </persName>
                  <email type="md5">6cda2a815dcec43eeed4e2ff051466ca</email>
                  <email type="domain">irt-saintexupery.com</email>
                  <idno type="idhal" notation="string">fanny-jourdan</idno>
                  <idno type="idhal" notation="numeric">1225483</idno>
                  <idno type="halauthorid" notation="string">2719582-1225483</idno>
                  <idno type="ARXIV">https://arxiv.org/a/jourdan_f_1</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=ntU8A30AAAAJ</idno>
                  <affiliation ref="#struct-417643"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Gabriel</forename>
                    <surname>Hautreux</surname>
                  </persName>
                  <idno type="halauthorid">980135-0</idno>
                  <affiliation ref="#struct-300898"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">João</forename>
                    <surname>Alves</surname>
                  </persName>
                  <idno type="halauthorid">402006-0</idno>
                  <affiliation ref="#struct-566893"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Kevin</forename>
                    <surname>El-Haddad</surname>
                  </persName>
                  <idno type="halauthorid">3734592-0</idno>
                  <affiliation ref="#struct-29983"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Manuel</forename>
                    <surname>Faysse</surname>
                  </persName>
                  <email type="md5">faba2cb4c50d2f16cc1a96f8f4a8ab56</email>
                  <email type="domain">centralesupelec.fr</email>
                  <idno type="idhal" notation="string">manuel-faysse</idno>
                  <idno type="idhal" notation="numeric">1511892</idno>
                  <idno type="halauthorid" notation="string">3148323-1511892</idno>
                  <idno type="GOOGLE SCHOLAR">ew4xsR4AAAAJ</idno>
                  <idno type="ARXIV">https://arxiv.org/a/faysse_m_1</idno>
                  <idno type="ORCID">https://orcid.org/0009-0009-3424-5800</idno>
                  <affiliation ref="#struct-1225281"/>
                  <affiliation ref="#struct-411575"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Maxime</forename>
                    <surname>Peyrard</surname>
                  </persName>
                  <email type="md5">d214b11d3f38faedb4b8c16401892a36</email>
                  <email type="domain">univ-grenoble-alpes.fr</email>
                  <idno type="idhal" notation="string">maxime-peyrard</idno>
                  <idno type="idhal" notation="numeric">1423948</idno>
                  <idno type="halauthorid" notation="string">2297120-1423948</idno>
                  <affiliation ref="#struct-1043313"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Nuno</forename>
                    <forename type="middle">M</forename>
                    <surname>Guerreiro</surname>
                  </persName>
                  <idno type="halauthorid">3149320-0</idno>
                  <affiliation ref="#struct-1042590"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Patrick</forename>
                    <surname>Fernandes</surname>
                  </persName>
                  <idno type="halauthorid">1547426-0</idno>
                  <affiliation ref="#struct-501124"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Ricardo</forename>
                    <surname>Rei</surname>
                  </persName>
                  <idno type="halauthorid">3149158-0</idno>
                  <affiliation ref="#struct-566893"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Pierre</forename>
                    <surname>Colombo</surname>
                  </persName>
                  <email type="md5">e2d5dac3d92757ed48e37e126a3464a3</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">pierre-colombo</idno>
                  <idno type="idhal" notation="numeric">743646</idno>
                  <idno type="halauthorid" notation="string">1007669-743646</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=yPoMt8gAAAAJ&amp;hl=fr</idno>
                  <idno type="IDREF">https://www.idref.fr/258975059</idno>
                  <affiliation ref="#struct-1042590"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">Second Conference on Language Modeling</title>
                <meeting>
                  <title>COLM 2025 - Second Conference on Language Modeling</title>
                  <date type="start">2025-10-07</date>
                  <date type="end">2025-10-10</date>
                  <settlement>Montreal</settlement>
                  <country key="CA">Canada</country>
                </meeting>
                <imprint>
                  <biblScope unit="pp">1-28</biblScope>
                  <date type="datePub">2025-03-10</date>
                </imprint>
              </monogr>
              <idno type="arxiv">2503.05500</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</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>Equal contribution, † Ordered alphabetically by the first name, ⋆ Senior advisor General-purpose multilingual vector representations, used in retrieval, regression, and classification, are traditionally obtained from bidirectional encoder models. Despite their wide applicability, encoders have been recently overshadowed by advances in generative decoder-only models. However, many innovations driving this progress are not inherently tied to decoders. In this paper, we revisit the development of multilingual encoders through the lens of these advances, and introduce EuroBERT, a family of multilingual encoders covering European and widely spoken global languages. Our models outperform existing alternatives across a diverse range of tasks, spanning multilingual capabilities, mathematics, and coding, and natively support sequences of up to 8,192 tokens. We also examine the design decisions behind EuroBERT, offering insights into our dataset composition and training pipeline. We publicly release the EuroBERT models, including intermediate training checkpoints, together with our training framework.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-1042590" status="VALID">
          <idno type="IdRef">14797299X</idno>
          <idno type="RNSR">200615286U</idno>
          <idno type="ROR">https://ror.org/03q29s414</idno>
          <orgName>Mathématiques et Informatique pour la Complexité et les Systèmes</orgName>
          <orgName type="acronym">MICS</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Plateau de Moulon 3 rue Joliot Curie 91192 GIF SUR YVETTE CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://mics.centralesupelec.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-411575" type="direct"/>
            <relation active="#struct-419361" type="direct"/>
          </listRelation>
        </org>
        <org type="regrouplaboratory" xml:id="struct-501124" status="OLD">
          <orgName>Instituto Superior Técnico</orgName>
          <date type="end">2013-12-31</date>
          <desc>
            <address>
              <addrLine>Department of Computer Science and Engineering, Instituto Superior Técnico, laboratory, pt (Tut.: Technical University of Lisbon) - Av. Rovisco Pais 1049-001 Lisboa Portugal</addrLine>
              <country key="PT"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-341794" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-419361" status="VALID">
          <idno type="IdRef">241345251</idno>
          <idno type="ROR">https://ror.org/03xjwb503</idno>
          <orgName>Université Paris-Saclay</orgName>
          <desc>
            <address>
              <addrLine>Bâtiment Bréguet, 3 Rue Joliot Curie 2e ét, 91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-paris-saclay.fr/fr</ref>
          </desc>
        </org>
        <org type="department" xml:id="struct-1065372" status="VALID">
          <orgName>Sciences et Technologies des Langues - LISN</orgName>
          <orgName type="acronym">STL</orgName>
          <date type="start">2021-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-1061259" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-419361" type="indirect"/>
            <relation name="UMR9015" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1061259" status="VALID">
          <idno type="IdRef">253160316</idno>
          <idno type="RNSR">202123711L</idno>
          <idno type="ROR">https://ror.org/00rd81916</idno>
          <idno type="Wikidata">Q109620676</idno>
          <orgName>Laboratoire Interdisciplinaire des Sciences du Numérique</orgName>
          <orgName type="acronym">LISN</orgName>
          <date type="start">2021-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Universitaire bât 507Rue du Belvédère91405 Orsay cedexet Campus Universitaire bât 6401 rue Raimond Castaing91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.lisn.upsaclay.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
            <relation active="#struct-411575" type="direct"/>
            <relation active="#struct-419361" type="direct"/>
            <relation name="UMR9015" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-1092628" status="OLD">
          <idno type="RNSR">201421145C</idno>
          <idno type="ROR">https://ror.org/00xkg0532</idno>
          <orgName>Creating and exploiting explicit links between multimedia fragments</orgName>
          <orgName type="acronym">LinkMedia</orgName>
          <date type="start">2022-01-01</date>
          <date type="end">2025-12-31</date>
          <desc>
            <address>
              <addrLine>Campus de Beaulieu 35042 Rennes cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www-linkmedia.irisa.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-419153" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-1092619" type="direct"/>
            <relation active="#struct-490899" type="indirect"/>
            <relation active="#struct-105160" type="indirect"/>
            <relation active="#struct-117606" type="indirect"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation active="#struct-172265" type="indirect"/>
            <relation active="#struct-247362" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation name="UMR6074" active="#struct-441569" type="indirect"/>
            <relation active="#struct-481355" type="indirect"/>
            <relation active="#struct-302102" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-117606" status="VALID">
          <idno type="ROR">https://ror.org/04xaa4j22</idno>
          <orgName>Institut National des Sciences Appliquées - Rennes</orgName>
          <orgName type="acronym">INSA Rennes</orgName>
          <desc>
            <address>
              <addrLine>20, avenue des Buttes de Coësmes - CS 70839 - 35708 Rennes cedex 7</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.insa-rennes.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301232" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-1063427" status="VALID">
          <orgName>Artefact [Paris]</orgName>
          <desc>
            <address>
              <addrLine>Artefact, 19 rue Richer 75009 Paris, France</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.artefact.com/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300898" status="VALID">
          <orgName>CINES</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-417643" status="VALID">
          <orgName>IRT Saint Exupéry - Institut de Recherche Technologique</orgName>
          <desc>
            <address>
              <addrLine>Bât B612, 3 rue Tarfaya,CS 34436, 31405 Toulouse Cedex 4 (France)</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.irt-saintexupery.com/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-566893" status="VALID">
          <orgName>Unbabel</orgName>
          <date type="start">2013-01-01</date>
          <desc>
            <address>
              <addrLine>Lisbon</addrLine>
              <country key="PT"/>
            </address>
            <ref type="url">https://unbabel.com/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-29983" status="VALID">
          <orgName>Institut Supérieur d'Informatique et d'Automatique</orgName>
          <orgName type="acronym">ISIA</orgName>
          <desc>
            <address>
              <addrLine>Mines Paris</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-301492" type="direct"/>
            <relation active="#struct-564132" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-1225281" status="VALID">
          <orgName>Illuin Technology</orgName>
          <date type="start">2017-01-01</date>
          <desc>
            <address>
              <addrLine>Tour EDF, 20 Pl. de la Défense, 92800 Puteaux, France</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.illuin.tech/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-411575" status="VALID">
          <idno type="IdRef">184443237</idno>
          <idno type="ROR">https://ror.org/019tcpt25</idno>
          <orgName>CentraleSupélec</orgName>
          <desc>
            <address>
              <addrLine>3, rue Joliot Curie,Plateau de Moulon,91192 GIF-SUR-YVETTE Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.centralesupelec.fr</ref>
          </desc>
        </org>
        <org type="researchteam" xml:id="struct-1043313" status="VALID">
          <orgName>Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole</orgName>
          <orgName type="acronym">GETALP</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Laboratoire LIG - Bâtiment IMAG - 700 avenue Centrale, CS 40700 - 38058 Grenoble cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://lig-getalp.imag.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1043301" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation name="UMR5217" active="#struct-441569" type="indirect"/>
            <relation active="#struct-1042703" type="indirect"/>
            <relation active="#struct-1043329" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-341794" status="OLD">
          <orgName>Technical University of Lisbon</orgName>
          <date type="start">1930-01-01</date>
          <date type="end">2013-01-01</date>
          <desc>
            <address>
              <country key="PT"/>
            </address>
          </desc>
        </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="laboratory" xml:id="struct-419153" status="VALID">
          <idno type="RNSR">198018249C</idno>
          <idno type="ROR">https://ror.org/04040yw90</idno>
          <orgName>Centre Inria de l'Université de Rennes</orgName>
          <desc>
            <address>
              <addrLine>Campus de beaulieu35042 Rennes cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/rennes</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
        <org type="department" xml:id="struct-1092619" status="VALID">
          <orgName>SIGNAL, IMAGE ET LANGAGE</orgName>
          <orgName type="acronym">IRISA-D6</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.irisa.fr/departements/media-interactions</ref>
          </desc>
          <listRelation>
            <relation active="#struct-490899" type="direct"/>
            <relation active="#struct-105160" type="indirect"/>
            <relation active="#struct-117606" type="indirect"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation active="#struct-172265" type="indirect"/>
            <relation active="#struct-247362" type="indirect"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation name="UMR6074" active="#struct-441569" type="indirect"/>
            <relation active="#struct-481355" type="indirect"/>
            <relation active="#struct-302102" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-490899" status="VALID">
          <idno type="IdRef">026386909</idno>
          <idno type="ISNI">0000 0001 2298 7270</idno>
          <idno type="RNSR">200012163A</idno>
          <idno type="ROR">https://ror.org/00myn0z94</idno>
          <orgName>Institut de Recherche en Informatique et Systèmes Aléatoires</orgName>
          <orgName type="acronym">IRISA</orgName>
          <date type="start">2017-01-01</date>
          <desc>
            <address>
              <addrLine>Avenue du général LeclercCampus de Beaulieu 35042 RENNES CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.irisa.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-105160" type="direct"/>
            <relation active="#struct-117606" type="direct"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation active="#struct-172265" type="direct"/>
            <relation active="#struct-247362" type="direct"/>
            <relation active="#struct-300009" type="direct"/>
            <relation active="#struct-411575" type="direct"/>
            <relation name="UMR6074" active="#struct-441569" type="direct"/>
            <relation active="#struct-481355" type="direct"/>
            <relation active="#struct-302102" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-105160" status="VALID">
          <idno type="IdRef">26693823X</idno>
          <idno type="ROR">https://ror.org/015m7wh34</idno>
          <orgName>Université de Rennes</orgName>
          <orgName type="acronym">UR</orgName>
          <desc>
            <address>
              <addrLine>Campus de Beaulieu, 263 avenue Général Leclerc, CS 74205, 35042 RENNES CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-rennes.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-301232" status="VALID">
          <idno type="IdRef">162105150</idno>
          <orgName>Institut National des Sciences Appliquées</orgName>
          <orgName type="acronym">INSA</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-172265" status="VALID">
          <idno type="IdRef">05017746X</idno>
          <idno type="ISNI">0000000121680285</idno>
          <idno type="ROR">https://ror.org/04ed7fw48</idno>
          <orgName>Université de Bretagne Sud</orgName>
          <orgName type="acronym">UBS</orgName>
          <date type="start">1995-02-07</date>
          <desc>
            <address>
              <addrLine>BP 92116 - 56321 Lorient cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-ubs.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-247362" status="VALID">
          <idno type="ROR">https://ror.org/03rxtdc22</idno>
          <orgName>École normale supérieure - Rennes</orgName>
          <orgName type="acronym">ENS Rennes</orgName>
          <desc>
            <address>
              <addrLine>Campus de Ker Lann - avenue Robert Schuman - 35170 Bruz</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ens-rennes.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-301492" status="VALID">
          <idno type="IdRef">026375249</idno>
          <idno type="ROR">https://ror.org/04y8cs423</idno>
          <orgName>Mines Paris - PSL (École nationale supérieure des mines de Paris)</orgName>
          <date type="start">1783-01-01</date>
          <desc>
            <address>
              <addrLine>60, boulevard Saint-Michel 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.minesparis.psl.eu/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-564132" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-564132" status="VALID">
          <idno type="IdRef">241597595</idno>
          <idno type="ISNI">0000 0004 1784 3645</idno>
          <idno type="ROR">https://ror.org/013cjyk83</idno>
          <orgName>Université Paris Sciences et Lettres</orgName>
          <orgName type="acronym">PSL</orgName>
          <desc>
            <address>
              <addrLine>60 rue Mazarine 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.psl.eu/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-1043301" status="VALID">
          <idno type="IdRef">148425550</idno>
          <idno type="ISNI">0000 0001 2286 4035</idno>
          <idno type="RNSR">200711886U</idno>
          <idno type="ROR">https://ror.org/01c8rcg82</idno>
          <orgName>Laboratoire d'Informatique de Grenoble</orgName>
          <orgName type="acronym">LIG</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>UMR 5217 - Laboratoire LIG - Bâtiment IMAG - 700 avenue Centrale - Domaine Universitaire de Saint-Martin-d’Hères Adresse postale : CS 40700 - 38058 Grenoble cedex 9Tél. : 04 57 42 14 00</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.liglab.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
            <relation name="UMR5217" active="#struct-441569" type="direct"/>
            <relation active="#struct-1042703" type="direct"/>
            <relation active="#struct-1043329" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-1042703" status="VALID">
          <idno type="IdRef">240648315</idno>
          <idno type="ROR">https://ror.org/02rx3b187</idno>
          <orgName>Université Grenoble Alpes</orgName>
          <orgName type="acronym">UGA</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Adresse CS 40700 - 38058 Grenoble cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-grenoble-alpes.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-1043329" status="VALID">
          <idno type="IdRef">026388804</idno>
          <idno type="ROR">https://ror.org/05sbt2524</idno>
          <orgName>Institut polytechnique de Grenoble - Grenoble Institute of Technology</orgName>
          <orgName type="acronym">Grenoble INP</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>46 avenue Félix Viallet 38031 Grenoble Cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.grenoble-inp.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1042703" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>