<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2026-lapr">
    <titleInfo>
        <title>LaPR: Latent Preference Reasoning for Generative Personalized Retrieval</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hanze</namePart>
        <namePart type="family">Guo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shunyu</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiakai</namePart>
        <namePart type="family">Tang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jingwei</namePart>
        <namePart type="family">Zhuo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yi</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xuanping</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiao</namePart>
        <namePart type="family">Zhou</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</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Generative retrieval offers a unified paradigm for personalized search by autoregressively decoding items as Semantic IDs. However, personalized search hinges on reasoning about query-history relevance, in which explicit textual reasoning incurs heavy cost and high latency, whereas purely implicit reasoning does not provide a structured intermediate latent interface for retrieval. To resolve this tension, we propose LaPR, an adaptive latent retrieval reasoning framework that turns explicit retrieval reasoning into compact latent signals. Specifically, LaPR constructs verified step-wise retrieval traces, induces step-conditioned semantic slots via vector quantization, and distills textual reasoning into these slots through a text-latent to pure-latent curriculum. At inference, LaPR adaptively predicts the reasoning depth and corresponding slots from the query and user history, providing latent reasoning signals for efficient Semantic-ID generation. Extensive experiments show that LaPR consistently surpasses all baselines, achieving SOTA personal retrieval performance while substantially reducing reasoning-token cost and inference latency.</abstract>
    <identifier type="citekey">guo-etal-2026-lapr</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2255/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>51279</start>
            <end>51297</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T LaPR: Latent Preference Reasoning for Generative Personalized Retrieval
%A Guo, Hanze
%A Zhang, Shunyu
%A Tang, Jiakai
%A Zhuo, Jingwei
%A Zhang, Yi
%A Li, Xuanping
%A Zhou, Xiao
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F guo-etal-2026-lapr
%X Generative retrieval offers a unified paradigm for personalized search by autoregressively decoding items as Semantic IDs. However, personalized search hinges on reasoning about query-history relevance, in which explicit textual reasoning incurs heavy cost and high latency, whereas purely implicit reasoning does not provide a structured intermediate latent interface for retrieval. To resolve this tension, we propose LaPR, an adaptive latent retrieval reasoning framework that turns explicit retrieval reasoning into compact latent signals. Specifically, LaPR constructs verified step-wise retrieval traces, induces step-conditioned semantic slots via vector quantization, and distills textual reasoning into these slots through a text-latent to pure-latent curriculum. At inference, LaPR adaptively predicts the reasoning depth and corresponding slots from the query and user history, providing latent reasoning signals for efficient Semantic-ID generation. Extensive experiments show that LaPR consistently surpasses all baselines, achieving SOTA personal retrieval performance while substantially reducing reasoning-token cost and inference latency.
%U https://aclanthology.org/2026.emnlp-main.2255/
%P 51279-51297

Markdown (Informal)

[LaPR: Latent Preference Reasoning for Generative Personalized Retrieval](https://aclanthology.org/2026.emnlp-main.2255/) (Guo et al., EMNLP 2026)

• LaPR: Latent Preference Reasoning for Generative Personalized Retrieval (Guo et al., EMNLP 2026)

ACL

• Hanze Guo, Shunyu Zhang, Jiakai Tang, Jingwei Zhuo, Yi Zhang, Xuanping Li, and Xiao Zhou. 2026. LaPR: Latent Preference Reasoning for Generative Personalized Retrieval. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 51279–51297, Budapest, Hungary. Association for Computational Linguistics.