<?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-04918564</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="2026-05-03T12:11:34+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Instruct-to-SPARQL: A text-to-SPARQL dataset for training Wikidata Agents</title>
            <author role="aut">
              <persName>
                <forename type="first">Alexis</forename>
                <surname>Strappazon</surname>
              </persName>
              <email type="md5">b1203986e4e188f3ed6ba191be9b723c</email>
              <email type="domain">insa-lyon.fr</email>
              <idno type="idhal" notation="numeric">1498872</idno>
              <idno type="halauthorid" notation="string">3393191-1498872</idno>
              <affiliation ref="#struct-394737"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Michael</forename>
                <surname>Granitzer</surname>
              </persName>
              <email type="md5">74ba8f22a6db5f0ca71b884e0b4af479</email>
              <email type="domain">uni-passau.de</email>
              <idno type="idhal" notation="numeric">1026059</idno>
              <idno type="halauthorid" notation="string">611099-1026059</idno>
              <affiliation ref="#struct-304235"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Előd</forename>
                <surname>Egyed-Zsigmond</surname>
              </persName>
              <idno type="halauthorid">658087-0</idno>
              <affiliation ref="#struct-394737"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Jelena</forename>
                <surname>Mitrovic</surname>
              </persName>
              <idno type="halauthorid">3393192-0</idno>
              <affiliation ref="#struct-304235"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Mehdi</forename>
                <surname>Ben Amor</surname>
              </persName>
              <email type="md5">7a70b56be7e095b313b9a21ed274f4c3</email>
              <email type="domain">uni-passau.de</email>
              <idno type="idhal" notation="numeric">1498873</idno>
              <idno type="halauthorid" notation="string">3393193-1498873</idno>
              <affiliation ref="#struct-304235"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Előd</forename>
                <surname>Egyed-Zsigmond</surname>
              </persName>
              <email type="md5">3572b4dfe3d6b64071d2c4d3a2a2df1f</email>
              <email type="domain">insa-lyon.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-01-29 10:53:00</date>
              <date type="whenModified">2025-09-03 10:07:24</date>
              <date type="whenReleased">2025-02-06 10:45:15</date>
              <date type="whenProduced">2025-03-24</date>
              <date type="whenEndEmbargoed">2025-01-29</date>
              <ref type="file" target="https://hal.science/hal-04918564v1/document">
                <date notBefore="2025-01-29"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-04918564v1/file/CHIIR_25_SPARQL_LLM.pdf" id="file-4918564-4269795">
                <date notBefore="2025-01-29"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="316546">
                <persName>
                  <forename>Előd</forename>
                  <surname>Egyed-Zsigmond</surname>
                </persName>
                <email type="md5">3572b4dfe3d6b64071d2c4d3a2a2df1f</email>
                <email type="domain">insa-lyon.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04918564</idno>
            <idno type="halUri">https://hal.science/hal-04918564</idno>
            <idno type="halBibtex">strappazon:hal-04918564</idno>
            <idno type="halRefHtml">&lt;i&gt;ACM SIGIR Conference on Human Information Interaction And Retrieval&lt;/i&gt;, ACM, Mar 2025, Melbourne (AUS), Australia. &lt;a target="_blank" href="https://dx.doi.org/10.1145/3698204.3716476"&gt;&amp;#x27E8;10.1145/3698204.3716476&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">ACM SIGIR Conference on Human Information Interaction And Retrieval, ACM, Mar 2025, Melbourne (AUS), Australia. &amp;#x27E8;10.1145/3698204.3716476&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-4918564-4269795"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UNIV-LYON1">Université Claude Bernard - Lyon I</idno>
            <idno type="stamp" n="UNIV-LYON2">Université Lumière Lyon 2</idno>
            <idno type="stamp" n="INSA-LYON">Institut National des Sciences Appliquées de Lyon</idno>
            <idno type="stamp" n="EC-LYON">Ecole Centrale de Lyon</idno>
            <idno type="stamp" n="LIRIS" corresp="UNIV-LYON1">Laboratoire d'InfoRmatique en Image et Systèmes d'information</idno>
            <idno type="stamp" n="LYON2">Université Lyon2</idno>
            <idno type="stamp" n="INSA-GROUPE">Groupe INSA</idno>
            <idno type="stamp" n="UDL">UDL</idno>
            <idno type="stamp" n="UNIV-LYON">Université de Lyon</idno>
            <idno type="stamp" n="HAL-LYON-2-NOUVELLE-VERSION">Nouvelle version portail </idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Instruct-to-SPARQL: A text-to-SPARQL dataset for training Wikidata Agents</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Alexis</forename>
                    <surname>Strappazon</surname>
                  </persName>
                  <email type="md5">b1203986e4e188f3ed6ba191be9b723c</email>
                  <email type="domain">insa-lyon.fr</email>
                  <idno type="idhal" notation="numeric">1498872</idno>
                  <idno type="halauthorid" notation="string">3393191-1498872</idno>
                  <affiliation ref="#struct-394737"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Michael</forename>
                    <surname>Granitzer</surname>
                  </persName>
                  <email type="md5">74ba8f22a6db5f0ca71b884e0b4af479</email>
                  <email type="domain">uni-passau.de</email>
                  <idno type="idhal" notation="numeric">1026059</idno>
                  <idno type="halauthorid" notation="string">611099-1026059</idno>
                  <affiliation ref="#struct-304235"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Előd</forename>
                    <surname>Egyed-Zsigmond</surname>
                  </persName>
                  <idno type="halauthorid">658087-0</idno>
                  <affiliation ref="#struct-394737"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Jelena</forename>
                    <surname>Mitrovic</surname>
                  </persName>
                  <idno type="halauthorid">3393192-0</idno>
                  <affiliation ref="#struct-304235"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Mehdi</forename>
                    <surname>Ben Amor</surname>
                  </persName>
                  <email type="md5">7a70b56be7e095b313b9a21ed274f4c3</email>
                  <email type="domain">uni-passau.de</email>
                  <idno type="idhal" notation="numeric">1498873</idno>
                  <idno type="halauthorid" notation="string">3393193-1498873</idno>
                  <affiliation ref="#struct-304235"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>ACM SIGIR Conference on Human Information Interaction And Retrieval</title>
                  <date type="start">2025-03-24</date>
                  <date type="end">2025-03-28</date>
                  <settlement>Melbourne (AUS)</settlement>
                  <country key="AU">Australia</country>
                </meeting>
                <respStmt>
                  <resp>conferenceOrganizer</resp>
                  <name>ACM</name>
                </respStmt>
                <imprint>
                  <publisher>ACM</publisher>
                </imprint>
              </monogr>
              <idno type="doi">10.1145/3698204.3716476</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Text-to-SPARQL</term>
                <term xml:lang="en">Large Language Models</term>
                <term xml:lang="en">Information Retrieval</term>
                <term xml:lang="en">Question answering SPARQL</term>
                <term xml:lang="en">Information systems → Information retrieval</term>
                <term xml:lang="en">CCS Concepts</term>
                <term xml:lang="en">Question answering SPARQL Information Retrieval Large Language Models Text-to-SPARQL</term>
                <term xml:lang="en">CCS Concepts Information systems → Information retrieval</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 rapid adoption of Large Language Models (LLMs) for search engines and fact-checking platforms necessitates enhancing their output accuracy. Retrieval Augmented Generation (RAG) mitigates hallucinations but requires semantically rich repositories like Wikidata. However, there is a lack of high-quality data to fine-tune LLMs for querying such knowledge bases. To address this gap, we propose a curated dataset with 2,771 unique queries for fine-tuning LLMs to generate accurate and syntactically valid SPARQL queries from natural language instructions. This dataset, customized for interaction with Wikidata, also serves as a robust benchmark for text-to-SPARQL task evaluation. Key findings show that models generally perform better on queries with lower complexity.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-394737" status="VALID">
          <orgName>Distribution, Recherche d'Information et Mobilité</orgName>
          <orgName type="acronym">DRIM</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-2003" type="direct"/>
            <relation active="#struct-33804" type="indirect"/>
            <relation active="#struct-126765" type="indirect"/>
            <relation active="#struct-301088" type="indirect"/>
            <relation active="#struct-194495" type="indirect"/>
            <relation active="#struct-219748" type="indirect"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation name="UMR5205" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-304235" status="VALID">
          <idno type="ROR">https://ror.org/05ydjnb78</idno>
          <orgName>Universität Passau [Passau]</orgName>
          <desc>
            <address>
              <addrLine>Innstraße 41, 94032 Passau</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">http://www.uni-passau.de/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-2003" status="VALID">
          <idno type="IdRef">149705271</idno>
          <idno type="ISNI">0000000122577669</idno>
          <idno type="RNSR">200511875R</idno>
          <idno type="ROR">https://ror.org/04dv4he91</idno>
          <orgName>Laboratoire d'InfoRmatique en Image et Systèmes d'information</orgName>
          <orgName type="acronym">LIRIS</orgName>
          <date type="start">2003-01-01</date>
          <desc>
            <address>
              <addrLine>Bâtiment Blaise Pascal - 20, avenue Albert Einstein - 69621 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://liris.cnrs.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-33804" type="direct"/>
            <relation active="#struct-126765" type="direct"/>
            <relation active="#struct-301088" type="indirect"/>
            <relation active="#struct-194495" type="direct"/>
            <relation active="#struct-219748" type="direct"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation name="UMR5205" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-33804" status="VALID">
          <idno type="IdRef">02640334X</idno>
          <idno type="ISNI">0000 0001 2188 0906</idno>
          <idno type="ROR">https://ror.org/03rth4p18</idno>
          <idno type="Wikidata">Q4041</idno>
          <orgName>Université Lumière - Lyon 2</orgName>
          <orgName type="acronym">UL2</orgName>
          <desc>
            <address>
              <addrLine>86, rue Pasteur - 69007 Lyon</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lyon2.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-126765" status="VALID">
          <idno type="ROR">https://ror.org/05s6rge65</idno>
          <orgName>École Centrale de Lyon</orgName>
          <orgName type="acronym">ECL</orgName>
          <desc>
            <address>
              <addrLine>36 avenue Guy de Collongue - 69134 Ecully cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ec-lyon.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301088" status="VALID">
          <idno type="ROR">https://ror.org/01rk35k63</idno>
          <orgName>Université de Lyon</orgName>
          <desc>
            <address>
              <addrLine>92 rue Pasteur - CS 30122, 69361 Lyon Cedex 07</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-lyon.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-194495" status="VALID">
          <idno type="IdRef">026402823</idno>
          <idno type="ISNI">0000000121686185</idno>
          <idno type="ROR">https://ror.org/029brtt94</idno>
          <orgName>Université Claude Bernard Lyon 1</orgName>
          <orgName type="acronym">UCBL</orgName>
          <desc>
            <address>
              <addrLine>43, boulevard du 11 novembre 1918, 69622 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lyon1.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-219748" status="VALID">
          <idno type="IdRef">052444724</idno>
          <idno type="ISNI">0000 0001 2292 0228</idno>
          <orgName>Institut National des Sciences Appliquées de Lyon</orgName>
          <orgName type="acronym">INSA Lyon</orgName>
          <date type="start">1957-03-18</date>
          <desc>
            <address>
              <addrLine>20 Avenue Albert Einstein, 69621 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.insa-lyon.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
            <relation active="#struct-301232" type="direct"/>
          </listRelation>
        </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="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>
      </listOrg>
    </back>
  </text>
</TEI>