<?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-05522699</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="2026-05-23T18:27:44+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Generating Complex Question Decompositions in the Face of Distribution Shifts</title>
            <author role="aut">
              <persName>
                <forename type="first">Kelvin</forename>
                <surname>Han</surname>
              </persName>
              <email type="md5">5d20904cd604920caae0241bd56b8d3d</email>
              <email type="domain">posteo.net</email>
              <idno type="idhal" notation="numeric">1649744</idno>
              <idno type="halauthorid" notation="string">1975332-1649744</idno>
              <affiliation ref="#struct-178243"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Claire</forename>
                <surname>Gardent</surname>
              </persName>
              <email type="md5">2011a70cc805f691b71fc804cd7fac0e</email>
              <email type="domain">loria.fr</email>
              <idno type="idhal" notation="string">claire-gardent</idno>
              <idno type="idhal" notation="numeric">3949</idno>
              <idno type="halauthorid" notation="string">16753-3949</idno>
              <idno type="IDREF">https://www.idref.fr/034104593</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-3805-6662</idno>
              <affiliation ref="#struct-178243"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Claire</forename>
                <surname>Gardent</surname>
              </persName>
              <email type="md5">2011a70cc805f691b71fc804cd7fac0e</email>
              <email type="domain">loria.fr</email>
            </editor>
            <funder ref="#projanr-185719"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2026-02-22 23:30:50</date>
              <date type="whenModified">2026-05-12 03:21:56</date>
              <date type="whenReleased">2026-02-23 14:06:08</date>
              <date type="whenProduced">2025-04-29</date>
              <date type="whenEndEmbargoed">2026-02-22</date>
              <ref type="file" target="https://hal.science/hal-05522699v1/document">
                <date notBefore="2026-02-22"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-05522699v1/file/2025.findings-ijcnlp.35.pdf" id="file-5522699-4727996">
                <date notBefore="2026-02-22"/>
              </ref>
              <ref type="annex" n="0" target="https://hal.science/hal-05522699v1/file/2025.inlg-main.26.pdf" id="file-5522699-4727997">
                <date notBefore="2026-02-22"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="103135">
                <persName>
                  <forename>Claire</forename>
                  <surname>Gardent</surname>
                </persName>
                <email type="md5">2011a70cc805f691b71fc804cd7fac0e</email>
                <email type="domain">loria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05522699</idno>
            <idno type="halUri">https://hal.science/hal-05522699</idno>
            <idno type="halBibtex">han:hal-05522699</idno>
            <idno type="halRefHtml">&lt;i&gt;2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics&lt;/i&gt;, ACL, Apr 2025, Alburquerque, United States</idno>
            <idno type="halRef">2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics, ACL, Apr 2025, Alburquerque, United States</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-5522699-4727996"/><ref corresp="#file-5522699-4727997"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="LORIA2">Publications du LORIA</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="UNIV-LORRAINE">Université de Lorraine</idno>
            <idno type="stamp" n="LORIA">Laboratoire Lorrain de Recherche en Informatique et ses Applications</idno>
            <idno type="stamp" n="LORIA-NLPKD" corresp="LORIA">Department of Natural Language Processing &amp; Knowledge Discovery</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="ACADEMIE-SCIENCES">Académie des sciences</idno>
            <idno type="stamp" n="ANR-IA-23" corresp="ANR-IA">ANR-IA-23</idno>
            <idno type="stamp" n="ANR-IA">ANR-IA</idno>
            <idno type="stamp" n="AM2I-UL">Pôle scientifique Automatique, Mathématiques, Informatique et leurs Intéractions de l'Université de Lorraine</idno>
            <idno type="stamp" n="ACADEMIE-SCIENCES-PUBLICATIONS-MEMBRES" corresp="ACADEMIE-SCIENCES">Publications des membres, correspondants et associés étrangers de l'Académie des sciences</idno>
            <idno type="stamp" n="ACADEMIE-SCIENCES-PUBLICATIONS-MEMBRES-3" corresp="ACADEMIE-SCIENCES-PUBLICATIONS-MEMBRES">Publications des membres de l'Académie des sciences (lot 3)</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">Generating Complex Question Decompositions in the Face of Distribution Shifts</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Kelvin</forename>
                    <surname>Han</surname>
                  </persName>
                  <email type="md5">5d20904cd604920caae0241bd56b8d3d</email>
                  <email type="domain">posteo.net</email>
                  <idno type="idhal" notation="numeric">1649744</idno>
                  <idno type="halauthorid" notation="string">1975332-1649744</idno>
                  <affiliation ref="#struct-178243"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Claire</forename>
                    <surname>Gardent</surname>
                  </persName>
                  <email type="md5">2011a70cc805f691b71fc804cd7fac0e</email>
                  <email type="domain">loria.fr</email>
                  <idno type="idhal" notation="string">claire-gardent</idno>
                  <idno type="idhal" notation="numeric">3949</idno>
                  <idno type="halauthorid" notation="string">16753-3949</idno>
                  <idno type="IDREF">https://www.idref.fr/034104593</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-3805-6662</idno>
                  <affiliation ref="#struct-178243"/>
                </author>
              </analytic>
              <monogr>
                <idno type="isbn">979-8-89176-189-6</idno>
                <meeting>
                  <title>2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics</title>
                  <date type="start">2025-04-29</date>
                  <date type="end">2025-05-04</date>
                  <settlement>Alburquerque</settlement>
                  <country key="US">United States</country>
                </meeting>
                <respStmt>
                  <resp>conferenceOrganizer</resp>
                  <name>ACL</name>
                </respStmt>
                <imprint>
                  <biblScope unit="serie">Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</biblScope>
                </imprint>
              </monogr>
              <ref type="publisher">https://2025.naacl.org/</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Generative AI</term>
                <term xml:lang="en">Natural Language Processing</term>
              </keywords>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</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>Question decomposition has been found to help large language models' (LLMs) performance on complex question answering (QA) by breaking these questions into simpler subquestions for answering. Nonetheless, performance on the task remains dominated by supervised approaches, suggesting room for making LLMs better decomposers. One way of improving LLM training and fine-tuning is to leverage synthetic training data, but the superior performance of supervised approaches collapses in the face of distribution shifts, making them unsuitable for generating synthetic data across new domains and at scale. To address this, we propose an approach to generate synthetic decomposition data with only five annotated examples; we do this by (i) extending recent advancements in using LLM-as-judge and for reranking in novel ways, as well as (ii) using a panel of smaller-sized LLMs for data generation instead of resource-intensive larger models. Through careful validation of our approach over two benchmark datasets, we show that our data generation and modelling approaches bring consistent improvements over using few-shot prompting with LLMs for the task.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-178243" status="VALID">
          <orgName>Natural Language Processing : representations, inference and semantics</orgName>
          <orgName type="acronym">SYNALP</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr/la-recherche-en/equipes/synalp</ref>
          </desc>
          <listRelation>
            <relation active="#struct-423086" type="direct"/>
            <relation active="#struct-206040" type="indirect"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-413289" type="indirect"/>
            <relation name="UMR7503" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="department" xml:id="struct-423086" status="VALID">
          <orgName>Department of Natural Language Processing &amp; Knowledge Discovery</orgName>
          <orgName type="acronym">LORIA - NLPKD</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr/en/research/departments/natural-language-processing-and-knowledge-discovery/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-206040" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-413289" type="indirect"/>
            <relation name="UMR7503" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-206040" status="VALID">
          <idno type="IdRef">067077927</idno>
          <idno type="ISNI">0000000121795429</idno>
          <idno type="RNSR">198912571S</idno>
          <idno type="IdUnivLorraine">[UL]RSI--</idno>
          <idno type="ROR">https://ror.org/02vnf0c38</idno>
          <orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
          <orgName type="acronym">LORIA</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
            <relation active="#struct-411575" type="direct"/>
            <relation active="#struct-413289" type="direct"/>
            <relation name="UMR7503" active="#struct-441569" 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="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-413289" status="VALID">
          <idno type="IdRef">157040569</idno>
          <idno type="IdUnivLorraine">[UL]100--</idno>
          <idno type="ROR">https://ror.org/04vfs2w97</idno>
          <orgName>Université de Lorraine</orgName>
          <orgName type="acronym">UL</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lorraine.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>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-185719" status="VALID">
          <idno type="anr">ANR-23-IACL-0004</idno>
          <orgName>ENACT</orgName>
          <desc>European Center on Artificial Intelligence Through Innovation</desc>
          <date type="start">2023</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>