<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="choi-etal-2025-word2passage">
    <titleInfo>
        <title>Word2Passage: Word-level Importance Re-weighting for Query Expansion</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jeonghwan</namePart>
        <namePart type="family">Choi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Minjeong</namePart>
        <namePart type="family">Ban</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Minseok</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hwanjun</namePart>
        <namePart type="family">Song</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>Retrieval-augmented generation (RAG) enhances the quality of LLM generation by providing relevant chunks, but retrieving accurately from external knowledge remains challenging due to missing contextually important words in query. We present Word2Passage, a novel approach that improves retrieval accuracy by optimizing word importance in query expansion. Our method generates references at word, sentence, and passage levels for query expansion, then determines word importance by considering both their reference level origin and characteristics derived from query types and corpus analysis. Specifically, our method assigns distinct importance scores to words based on whether they originate from word, sentence, or passage-level references. Extensive experiments demonstrate that Word2Passage outperforms existing methods across various datasets and LLM configurations, effectively enhancing both retrieval accuracy and generation quality. The code is publicly available at https://github.com/DISL-Lab/Word2Passage</abstract>
    <identifier type="citekey">choi-etal-2025-word2passage</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.434</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.434/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>8276</start>
            <end>8296</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Word2Passage: Word-level Importance Re-weighting for Query Expansion
%A Choi, Jeonghwan
%A Ban, Minjeong
%A Kim, Minseok
%A Song, Hwanjun
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F choi-etal-2025-word2passage
%X Retrieval-augmented generation (RAG) enhances the quality of LLM generation by providing relevant chunks, but retrieving accurately from external knowledge remains challenging due to missing contextually important words in query. We present Word2Passage, a novel approach that improves retrieval accuracy by optimizing word importance in query expansion. Our method generates references at word, sentence, and passage levels for query expansion, then determines word importance by considering both their reference level origin and characteristics derived from query types and corpus analysis. Specifically, our method assigns distinct importance scores to words based on whether they originate from word, sentence, or passage-level references. Extensive experiments demonstrate that Word2Passage outperforms existing methods across various datasets and LLM configurations, effectively enhancing both retrieval accuracy and generation quality. The code is publicly available at https://github.com/DISL-Lab/Word2Passage
%R 10.18653/v1/2025.findings-acl.434
%U https://aclanthology.org/2025.findings-acl.434/
%U https://doi.org/10.18653/v1/2025.findings-acl.434
%P 8276-8296

Markdown (Informal)

[Word2Passage: Word-level Importance Re-weighting for Query Expansion](https://aclanthology.org/2025.findings-acl.434/) (Choi et al., Findings 2025)

• Word2Passage: Word-level Importance Re-weighting for Query Expansion (Choi et al., Findings 2025)

ACL

• Jeonghwan Choi, Minjeong Ban, Minseok Kim, and Hwanjun Song. 2025. Word2Passage: Word-level Importance Re-weighting for Query Expansion. In Findings of the Association for Computational Linguistics: ACL 2025, pages 8276–8296, Vienna, Austria. Association for Computational Linguistics.