<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="son-etal-2026-rcem">
    <titleInfo>
        <title>RCEM: Robust Conversational Search EMbedder in Distributional Shift</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kilho</namePart>
        <namePart type="family">Son</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bo-June</namePart>
        <namePart type="given">Paul</namePart>
        <namePart type="family">Hsu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Cha</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dinei</namePart>
        <namePart type="family">Florencio</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Pepa</namePart>
            <namePart type="family">Atanasova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gholamreza</namePart>
            <namePart type="family">Haffari</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Minghan</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-460-6</identifier>
    </relatedItem>
    <abstract>We propose RCEM, a Robust Conversational search EMbedder that augments text embedders with LLM query reformulation capabilities while approximately preserving their original generalization performance. Unlike prior conversational dense retrieval approaches that learn direct conversation-to-passage matching, RCEM aligns conversations, prepended by special token, to LLM-rewritten queries, while attempting to preserve the original embedding space. The approximately preserved embedding space automatically maps the rewritten queries to the relevant passages. As a result, RCEM (1) reduces overfitting by aligning conversations to shorter rewritten queries rather than full passages, (2) eliminates the need for conversation-to-passage relevance labels for training, and (3) approximately preserves the original embedding space, enabling conversational retrieval over indexes built by the base embedder without re-indexing. Extensive experiments show that RCEM consistently outperforms prior approaches, improving up to 30% retrieval accuracy under distributional shift.</abstract>
    <identifier type="citekey">son-etal-2026-rcem</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-industry.167/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>2830</start>
            <end>2843</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T RCEM: Robust Conversational Search EMbedder in Distributional Shift
%A Son, Kilho
%A Hsu, Bo-June Paul
%A Zhang, Cha
%A Florencio, Dinei
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F son-etal-2026-rcem
%X We propose RCEM, a Robust Conversational search EMbedder that augments text embedders with LLM query reformulation capabilities while approximately preserving their original generalization performance. Unlike prior conversational dense retrieval approaches that learn direct conversation-to-passage matching, RCEM aligns conversations, prepended by special token, to LLM-rewritten queries, while attempting to preserve the original embedding space. The approximately preserved embedding space automatically maps the rewritten queries to the relevant passages. As a result, RCEM (1) reduces overfitting by aligning conversations to shorter rewritten queries rather than full passages, (2) eliminates the need for conversation-to-passage relevance labels for training, and (3) approximately preserves the original embedding space, enabling conversational retrieval over indexes built by the base embedder without re-indexing. Extensive experiments show that RCEM consistently outperforms prior approaches, improving up to 30% retrieval accuracy under distributional shift.
%U https://aclanthology.org/2026.emnlp-industry.167/
%P 2830-2843

Markdown (Informal)

[RCEM: Robust Conversational Search EMbedder in Distributional Shift](https://aclanthology.org/2026.emnlp-industry.167/) (Son et al., EMNLP 2026)

• RCEM: Robust Conversational Search EMbedder in Distributional Shift (Son et al., EMNLP 2026)

ACL

• Kilho Son, Bo-June Paul Hsu, Cha Zhang, and Dinei Florencio. 2026. RCEM: Robust Conversational Search EMbedder in Distributional Shift. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 2830–2843, Budapest, Hungary. Association for Computational Linguistics.