@inproceedings{bi-etal-2025-consistency,
title = "Consistency-Aware Online Multi-Objective Alignment for Related Search Query Generation",
author = "Bi, Shuxian and
Gao, Chongming and
Wang, Wenjie and
Mou, Yueqi and
Wang, Chenxu and
Biao, Tang and
Yan, Peng and
Feng, Fuli",
editor = "Rehm, Georg and
Li, Yunyao",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-industry.96/",
doi = "10.18653/v1/2025.acl-industry.96",
pages = "1365--1377",
ISBN = "979-8-89176-288-6",
abstract = "Modern digital platforms rely on related search query recommendations to enhance engagement, yet existing methods fail to reconcile click-through rate (CTR) optimization with topic expansion. We propose **CMAQ**, a **C**onsistent **M**ulti-Objective **A**ligned **Q**uery generation framework that harmonizes these goals through three components: (1) reward modeling to quantify objectives, (2) style alignment for format compliance, and (3) consistency-aware optimization to coordinate joint improvements. CMAQ employs adaptive $\beta$-scaled DPO with geometric mean rewards, balancing CTR and expansion while mitigating objective conflicts. Extensive offline and online evaluations in a large-scale industrial setting demonstrate CMAQ{'}s superiority, achieving significant CTR gains (+2.3{\%}) and higher human-rated query quality compared to state-of-the-art methods. Our approach enables high-quality query generation while sustaining user engagement and platform ecosystem health."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bi-etal-2025-consistency">
<titleInfo>
<title>Consistency-Aware Online Multi-Objective Alignment for Related Search Query Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuxian</namePart>
<namePart type="family">Bi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chongming</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yueqi</namePart>
<namePart type="family">Mou</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">Tang</namePart>
<namePart type="family">Biao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fuli</namePart>
<namePart type="family">Feng</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>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</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">979-8-89176-288-6</identifier>
</relatedItem>
<abstract>Modern digital platforms rely on related search query recommendations to enhance engagement, yet existing methods fail to reconcile click-through rate (CTR) optimization with topic expansion. We propose **CMAQ**, a **C**onsistent **M**ulti-Objective **A**ligned **Q**uery generation framework that harmonizes these goals through three components: (1) reward modeling to quantify objectives, (2) style alignment for format compliance, and (3) consistency-aware optimization to coordinate joint improvements. CMAQ employs adaptive β-scaled DPO with geometric mean rewards, balancing CTR and expansion while mitigating objective conflicts. Extensive offline and online evaluations in a large-scale industrial setting demonstrate CMAQ’s superiority, achieving significant CTR gains (+2.3%) and higher human-rated query quality compared to state-of-the-art methods. Our approach enables high-quality query generation while sustaining user engagement and platform ecosystem health.</abstract>
<identifier type="citekey">bi-etal-2025-consistency</identifier>
<identifier type="doi">10.18653/v1/2025.acl-industry.96</identifier>
<location>
<url>https://aclanthology.org/2025.acl-industry.96/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1365</start>
<end>1377</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Consistency-Aware Online Multi-Objective Alignment for Related Search Query Generation
%A Bi, Shuxian
%A Gao, Chongming
%A Wang, Wenjie
%A Mou, Yueqi
%A Wang, Chenxu
%A Biao, Tang
%A Yan, Peng
%A Feng, Fuli
%Y Rehm, Georg
%Y Li, Yunyao
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-288-6
%F bi-etal-2025-consistency
%X Modern digital platforms rely on related search query recommendations to enhance engagement, yet existing methods fail to reconcile click-through rate (CTR) optimization with topic expansion. We propose **CMAQ**, a **C**onsistent **M**ulti-Objective **A**ligned **Q**uery generation framework that harmonizes these goals through three components: (1) reward modeling to quantify objectives, (2) style alignment for format compliance, and (3) consistency-aware optimization to coordinate joint improvements. CMAQ employs adaptive β-scaled DPO with geometric mean rewards, balancing CTR and expansion while mitigating objective conflicts. Extensive offline and online evaluations in a large-scale industrial setting demonstrate CMAQ’s superiority, achieving significant CTR gains (+2.3%) and higher human-rated query quality compared to state-of-the-art methods. Our approach enables high-quality query generation while sustaining user engagement and platform ecosystem health.
%R 10.18653/v1/2025.acl-industry.96
%U https://aclanthology.org/2025.acl-industry.96/
%U https://doi.org/10.18653/v1/2025.acl-industry.96
%P 1365-1377
Markdown (Informal)
[Consistency-Aware Online Multi-Objective Alignment for Related Search Query Generation](https://aclanthology.org/2025.acl-industry.96/) (Bi et al., ACL 2025)
ACL
- Shuxian Bi, Chongming Gao, Wenjie Wang, Yueqi Mou, Chenxu Wang, Tang Biao, Peng Yan, and Fuli Feng. 2025. Consistency-Aware Online Multi-Objective Alignment for Related Search Query Generation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track), pages 1365–1377, Vienna, Austria. Association for Computational Linguistics.