@inproceedings{li-etal-2026-dvcqr,
title = "{DVCQR}: Dual-View Conversational Query Rewriting with Stage-wise Reinforcement Learning",
author = "Li, Chenyi and
Tu, Xinhui and
Wang, Zaixiang",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1054/",
pages = "22993--23014",
ISBN = "979-8-89176-390-6",
abstract = "Conversational query rewriting (CQR) addresses context dependence in conversational search by rewriting each user query into a standalone form. Recent approaches leverage reinforcement learning (RL) to directly optimize retrieval effectiveness; however, they typically rely on a single rewrite, which struggles to accommodate the divergent preferences of sparse and dense retrievers and often suffers from conflicting optimization signals. We propose DVCQR, a Dual-View CQR framework that explicitly generates two complementary rewrites for each query: a sparse-view rewrite that emphasizes distinctive lexical anchors, and a dense-view rewrite that captures complete semantic constraints. Both rewrites are produced in a single pass via a structured reasoning process. To further mitigate objective conflicts, we introduce a stage-wise RL strategy that sequentially aligns the sparse and dense views with their corresponding retrievers using rank-based feedback. Extensive experiments on four benchmarks (TopiOCQA, QReCC, CAsT-19, and CAsT-20) demonstrate that DVCQR consistently outperforms state-of-the-art methods on most metrics under both sparse and dense retrieval settings, validating the effectiveness of dual-view rewriting and stage-wise retriever alignment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-dvcqr">
<titleInfo>
<title>DVCQR: Dual-View Conversational Query Rewriting with Stage-wise Reinforcement Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chenyi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinhui</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaixiang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Conversational query rewriting (CQR) addresses context dependence in conversational search by rewriting each user query into a standalone form. Recent approaches leverage reinforcement learning (RL) to directly optimize retrieval effectiveness; however, they typically rely on a single rewrite, which struggles to accommodate the divergent preferences of sparse and dense retrievers and often suffers from conflicting optimization signals. We propose DVCQR, a Dual-View CQR framework that explicitly generates two complementary rewrites for each query: a sparse-view rewrite that emphasizes distinctive lexical anchors, and a dense-view rewrite that captures complete semantic constraints. Both rewrites are produced in a single pass via a structured reasoning process. To further mitigate objective conflicts, we introduce a stage-wise RL strategy that sequentially aligns the sparse and dense views with their corresponding retrievers using rank-based feedback. Extensive experiments on four benchmarks (TopiOCQA, QReCC, CAsT-19, and CAsT-20) demonstrate that DVCQR consistently outperforms state-of-the-art methods on most metrics under both sparse and dense retrieval settings, validating the effectiveness of dual-view rewriting and stage-wise retriever alignment.</abstract>
<identifier type="citekey">li-etal-2026-dvcqr</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1054/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>22993</start>
<end>23014</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DVCQR: Dual-View Conversational Query Rewriting with Stage-wise Reinforcement Learning
%A Li, Chenyi
%A Tu, Xinhui
%A Wang, Zaixiang
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F li-etal-2026-dvcqr
%X Conversational query rewriting (CQR) addresses context dependence in conversational search by rewriting each user query into a standalone form. Recent approaches leverage reinforcement learning (RL) to directly optimize retrieval effectiveness; however, they typically rely on a single rewrite, which struggles to accommodate the divergent preferences of sparse and dense retrievers and often suffers from conflicting optimization signals. We propose DVCQR, a Dual-View CQR framework that explicitly generates two complementary rewrites for each query: a sparse-view rewrite that emphasizes distinctive lexical anchors, and a dense-view rewrite that captures complete semantic constraints. Both rewrites are produced in a single pass via a structured reasoning process. To further mitigate objective conflicts, we introduce a stage-wise RL strategy that sequentially aligns the sparse and dense views with their corresponding retrievers using rank-based feedback. Extensive experiments on four benchmarks (TopiOCQA, QReCC, CAsT-19, and CAsT-20) demonstrate that DVCQR consistently outperforms state-of-the-art methods on most metrics under both sparse and dense retrieval settings, validating the effectiveness of dual-view rewriting and stage-wise retriever alignment.
%U https://aclanthology.org/2026.acl-long.1054/
%P 22993-23014
Markdown (Informal)
[DVCQR: Dual-View Conversational Query Rewriting with Stage-wise Reinforcement Learning](https://aclanthology.org/2026.acl-long.1054/) (Li et al., ACL 2026)
ACL