<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-beyond-query">
    <titleInfo>
        <title>Beyond Query-Item Matching: Personalized Behavioral Relevance Modeling for E-commerce Search via Rubric-Guided Reinforcement Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chenxu</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jianzhi</namePart>
        <namePart type="family">Shao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jun</namePart>
        <namePart type="family">Ji</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaozhou</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhe</namePart>
        <namePart type="family">Sun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wei</namePart>
        <namePart type="family">Hu</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>E-commerce search systems typically separate query-item relevance matching from downstream personalized ranking. While effective for large-scale serving, this design leaves relevance levels dominated by objective query-item matching, forcing follow-up ranking to operate over candidate structures that may not reflect user behavioral preference. We define a new personalized behavioral relevance task, which predicts whether a relevance-stage candidate item is supported by the user’s behavioral evidence under current query intent. We develop a corresponding framework, BRIDGE, for Behavioral Relevance Inference with Dynamic Guidance from Evidence. It organizes multi-timescale behavioral context from online logs, obtains reliable supervision with multi-perspective annotation and adjudication, and trains an LLM to produce structured evidence-grounded decision rationales. It particularly incorporates sample-specific rubric rewards into GRPO to improve generated reasoning traces. Offline experiments validate that BRIDGE improves both prediction accuracy and reasoning quality. Online A/B tests show gains of 0.19% in active user-days and 0.67% in transaction-related user-days, both significant in statistics.</abstract>
    <identifier type="citekey">liu-etal-2026-beyond-query</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-industry.86/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1444</start>
            <end>1455</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Beyond Query-Item Matching: Personalized Behavioral Relevance Modeling for E-commerce Search via Rubric-Guided Reinforcement Learning
%A Liu, Yang
%A Wang, Chenxu
%A Shao, Jianzhi
%A Ji, Jun
%A Xu, Xiaozhou
%A Sun, Zhe
%A Hu, Wei
%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 liu-etal-2026-beyond-query
%X E-commerce search systems typically separate query-item relevance matching from downstream personalized ranking. While effective for large-scale serving, this design leaves relevance levels dominated by objective query-item matching, forcing follow-up ranking to operate over candidate structures that may not reflect user behavioral preference. We define a new personalized behavioral relevance task, which predicts whether a relevance-stage candidate item is supported by the user’s behavioral evidence under current query intent. We develop a corresponding framework, BRIDGE, for Behavioral Relevance Inference with Dynamic Guidance from Evidence. It organizes multi-timescale behavioral context from online logs, obtains reliable supervision with multi-perspective annotation and adjudication, and trains an LLM to produce structured evidence-grounded decision rationales. It particularly incorporates sample-specific rubric rewards into GRPO to improve generated reasoning traces. Offline experiments validate that BRIDGE improves both prediction accuracy and reasoning quality. Online A/B tests show gains of 0.19% in active user-days and 0.67% in transaction-related user-days, both significant in statistics.
%U https://aclanthology.org/2026.emnlp-industry.86/
%P 1444-1455

Markdown (Informal)

[Beyond Query-Item Matching: Personalized Behavioral Relevance Modeling for E-commerce Search via Rubric-Guided Reinforcement Learning](https://aclanthology.org/2026.emnlp-industry.86/) (Liu et al., EMNLP 2026)

• Beyond Query-Item Matching: Personalized Behavioral Relevance Modeling for E-commerce Search via Rubric-Guided Reinforcement Learning (Liu et al., EMNLP 2026)

ACL

• Yang Liu, Chenxu Wang, Jianzhi Shao, Jun Ji, Xiaozhou Xu, Zhe Sun, and Wei Hu. 2026. Beyond Query-Item Matching: Personalized Behavioral Relevance Modeling for E-commerce Search via Rubric-Guided Reinforcement Learning. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1444–1455, Budapest, Hungary. Association for Computational Linguistics.