<?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-04015863v2</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="2026-05-25T04:39:59+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM</title>
            <author role="aut">
              <persName>
                <forename type="first">Rachel</forename>
                <surname>Bawden</surname>
              </persName>
              <email type="md5">a08b8a5ca6961e673dd659fdfe33c881</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">rachel-bawden</idno>
              <idno type="idhal" notation="numeric">9441</idno>
              <idno type="halauthorid" notation="string">28540-9441</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-9553-1768</idno>
              <idno type="IDREF">https://www.idref.fr/233174591</idno>
              <idno type="ARXIV">https://arxiv.org/a/bawden_r_1</idno>
              <affiliation ref="#struct-482775"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">François</forename>
                <surname>Yvon</surname>
              </persName>
              <email type="md5">c62025aca0c6cf8d65b4fe9600c991af</email>
              <email type="domain">cnrs.fr</email>
              <idno type="idhal" notation="string">francois-yvon</idno>
              <idno type="idhal" notation="numeric">5347</idno>
              <idno type="halauthorid" notation="string">2529017-5347</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7972-7442</idno>
              <idno type="IDREF">https://www.idref.fr/057593531</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=JjfDvawAAAAJ</idno>
              <idno type="ARXIV">https://arxiv.org/a/yvon_f_1</idno>
              <affiliation ref="#struct-1062143"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Rachel</forename>
                <surname>Bawden</surname>
              </persName>
              <email type="md5">a08b8a5ca6961e673dd659fdfe33c881</email>
              <email type="domain">inria.fr</email>
            </editor>
            <funder ref="#projanr-50388"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1">
              <date type="whenSubmitted">2023-03-06 10:53:50</date>
            </edition>
            <edition n="v2" type="current">
              <date type="whenSubmitted">2023-05-09 14:26:12</date>
              <date type="whenWritten">2023</date>
              <date type="whenModified">2025-09-12 17:04:02</date>
              <date type="whenReleased">2023-05-10 16:34:21</date>
              <date type="whenProduced">2023-06-12</date>
              <date type="whenEndEmbargoed">2023-05-09</date>
              <ref type="file" target="https://inria.hal.science/hal-04015863v2/document">
                <date notBefore="2023-05-09"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-04015863v2/file/eamt23.pdf" id="file-4092614-3562762">
                <date notBefore="2023-05-09"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/2303.01911"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="197025">
                <persName>
                  <forename>Rachel</forename>
                  <surname>Bawden</surname>
                </persName>
                <email type="md5">a08b8a5ca6961e673dd659fdfe33c881</email>
                <email type="domain">inria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04015863</idno>
            <idno type="halUri">https://inria.hal.science/hal-04015863</idno>
            <idno type="halBibtex">bawden:hal-04015863</idno>
            <idno type="halRefHtml">&lt;i&gt;24th Annual Conference of the European Association for Machine Translation (EAMT 2023)&lt;/i&gt;, Jun 2023, Tampere, Finland. &lt;a target="_blank" href="https://dx.doi.org/10.48550/ARXIV.2303.01911"&gt;&amp;#x27E8;10.48550/ARXIV.2303.01911&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">24th Annual Conference of the European Association for Machine Translation (EAMT 2023), Jun 2023, Tampere, Finland. &amp;#x27E8;10.48550/ARXIV.2303.01911&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by-sa/4.0/">CC BY-SA 4.0 - Attribution - ShareAlike<ref corresp="#file-4092614-3562762"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <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="INRIA-ROCQ">INRIA Paris - Rocquencourt</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="GENCI">Publications ayant eu recours aux supercalculateurs du GENCI</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="PNRIA">Programme National de Recherche en IA</idno>
            <idno type="stamp" n="UNIVERSITE-PARIS-SACLAY" corresp="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="PRAIRIE-IA">PaRis AI Research InstitutE</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="LISN-TLP" corresp="LISN">Traitement du Langage Parlé </idno>
            <idno type="stamp" n="LISN-STL">Sciences et Technologies des Langues</idno>
            <idno type="stamp" n="ANR-IA-19" corresp="ANR-IA">ANR-IA-19</idno>
            <idno type="stamp" n="ANR-IA">ANR-IA</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Rachel</forename>
                    <surname>Bawden</surname>
                  </persName>
                  <email type="md5">a08b8a5ca6961e673dd659fdfe33c881</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">rachel-bawden</idno>
                  <idno type="idhal" notation="numeric">9441</idno>
                  <idno type="halauthorid" notation="string">28540-9441</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-9553-1768</idno>
                  <idno type="IDREF">https://www.idref.fr/233174591</idno>
                  <idno type="ARXIV">https://arxiv.org/a/bawden_r_1</idno>
                  <affiliation ref="#struct-482775"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">François</forename>
                    <surname>Yvon</surname>
                  </persName>
                  <email type="md5">c62025aca0c6cf8d65b4fe9600c991af</email>
                  <email type="domain">cnrs.fr</email>
                  <idno type="idhal" notation="string">francois-yvon</idno>
                  <idno type="idhal" notation="numeric">5347</idno>
                  <idno type="halauthorid" notation="string">2529017-5347</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7972-7442</idno>
                  <idno type="IDREF">https://www.idref.fr/057593531</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=JjfDvawAAAAJ</idno>
                  <idno type="ARXIV">https://arxiv.org/a/yvon_f_1</idno>
                  <affiliation ref="#struct-1062143"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">Proceedings of the 24th Annual Conference of the European Association for Machine Translation</title>
                <meeting>
                  <title>24th Annual Conference of the European Association for Machine Translation (EAMT 2023)</title>
                  <date type="start">2023-06-12</date>
                  <date type="end">2023-06-15</date>
                  <settlement>Tampere</settlement>
                  <country key="FI">Finland</country>
                </meeting>
                <imprint>
                  <date type="datePub">2023-03-03</date>
                </imprint>
              </monogr>
              <idno type="arxiv">2303.01911</idno>
              <idno type="doi">10.48550/ARXIV.2303.01911</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Evaluation</term>
                <term xml:lang="en">Large language models</term>
                <term xml:lang="en">LLMs</term>
                <term xml:lang="en">MT</term>
                <term xml:lang="en">NMT</term>
                <term xml:lang="en">Machine translation</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-cl">Computer Science [cs]/Computation and Language [cs.CL]</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 NLP community recently saw the release of a new large open-access multilingual language model, BLOOM (BigScience et al., 2022) covering 46 languages. We focus on BLOOM's multilingual ability by evaluating its machine translation performance across several datasets (WMT, Flores-101 and DiaBLa) and language pairs (high- and low-resourced). Our results show that 0-shot performance suffers from overgeneration and generating in the wrong language, but this is greatly improved in the few-shot setting, with very good results for a number of language pairs. We study several aspects including prompt design, model sizes, cross-lingual transfer and the use of discursive context.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-482775" status="VALID">
          <idno type="RNSR">201722248N</idno>
          <idno type="ROR">https://ror.org/05rnwy495</idno>
          <orgName>Automatic Language Modelling and ANAlysis &amp; Computational Humanities</orgName>
          <orgName type="acronym">ALMAnaCH</orgName>
          <date type="start">2017-01-01</date>
          <date type="end">2029-04-30</date>
          <desc>
            <address>
              <addrLine>48 Rue Barrault, 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.inria.fr/equipes/almanach</ref>
          </desc>
          <listRelation>
            <relation active="#struct-454310" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-1062143" status="OLD">
          <orgName>Traitement du Langage Parlé - LISN</orgName>
          <orgName type="acronym">TLP</orgName>
          <date type="start">2021-01-01</date>
          <desc>
            <address>
              <addrLine>Université Paris-Saclay, Bâtiment 507, 91405 Orsay Cedex</addrLine>
              <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"/>
            <relation active="#struct-1065372" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-454310" status="VALID">
          <idno type="IdRef">241614864</idno>
          <idno type="RNSR">196718247G</idno>
          <idno type="ROR">https://ror.org/05eyd5d35</idno>
          <orgName>Centre Inria de Paris</orgName>
          <date type="start">2016-03-10</date>
          <desc>
            <address>
              <addrLine>48 Rue Barrault, 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/paris</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300009" status="VALID">
          <idno type="ROR">https://ror.org/02kvxyf05</idno>
          <orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
          <orgName type="acronym">Inria</orgName>
          <desc>
            <address>
              <addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/en/</ref>
          </desc>
        </org>
        <org type="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="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="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="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="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>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-50388" status="VALID">
          <idno type="anr">ANR-19-P3IA-0001</idno>
          <orgName>PRAIRIE</orgName>
          <desc>PaRis Artificial Intelligence Research InstitutE</desc>
          <date type="start">2019</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>