@inproceedings{ye-etal-2025-q,
title = "{Q}-{PRM}: Adaptive Query Rewriting for Retrieval-Augmented Generation via Step-level Process Supervision",
author = "Ye, Xiaopeng and
Xu, Chen and
Zhang, Chaoliang and
Du, Zhaocheng and
Xu, Jun and
Wang, Gang and
Dong, Zhenhua",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.817/",
pages = "15113--15128",
ISBN = "979-8-89176-335-7",
abstract = "Query rewriting plays a pivotal role in Retrieval-Augmented Generation (RAG) by refining real-world queries of varying complexity. Existing approaches typically rely on outcome-supervised training or heuristic rules to guide the rewriting process. However, these paradigms often struggle to handle queries with varying levels of complexity, posing over- and under-refinement problems. We identify the root cause of these issues as the absence of supervision signals for intermediate steps. To fully construct and utilize such signals, we propose Q-PRM, a novel query rewriting framework. Q-PRM reformulates the rewriting process as a Markov Decision Process (MDP) composed of atomic rewriting steps. In this way, Q-PRM can apply process-level supervision to each atomic step according to the query type, offering more targeted and effective guidance. Q-PRM comprises three key stages: (1) applying Monte Carlo Tree Search to generate step-level process supervision signals; (2) performing reinforced self-training for progressive process refinement; and (3) employing PRM-guided decoding during inference. Experiments on several open-domain QA benchmarks demonstrate that Q-PRM consistently outperforms baselines across different levels of query complexity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ye-etal-2025-q">
<titleInfo>
<title>Q-PRM: Adaptive Query Rewriting for Retrieval-Augmented Generation via Step-level Process Supervision</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaopeng</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chaoliang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaocheng</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenhua</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Query rewriting plays a pivotal role in Retrieval-Augmented Generation (RAG) by refining real-world queries of varying complexity. Existing approaches typically rely on outcome-supervised training or heuristic rules to guide the rewriting process. However, these paradigms often struggle to handle queries with varying levels of complexity, posing over- and under-refinement problems. We identify the root cause of these issues as the absence of supervision signals for intermediate steps. To fully construct and utilize such signals, we propose Q-PRM, a novel query rewriting framework. Q-PRM reformulates the rewriting process as a Markov Decision Process (MDP) composed of atomic rewriting steps. In this way, Q-PRM can apply process-level supervision to each atomic step according to the query type, offering more targeted and effective guidance. Q-PRM comprises three key stages: (1) applying Monte Carlo Tree Search to generate step-level process supervision signals; (2) performing reinforced self-training for progressive process refinement; and (3) employing PRM-guided decoding during inference. Experiments on several open-domain QA benchmarks demonstrate that Q-PRM consistently outperforms baselines across different levels of query complexity.</abstract>
<identifier type="citekey">ye-etal-2025-q</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.817/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>15113</start>
<end>15128</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Q-PRM: Adaptive Query Rewriting for Retrieval-Augmented Generation via Step-level Process Supervision
%A Ye, Xiaopeng
%A Xu, Chen
%A Zhang, Chaoliang
%A Du, Zhaocheng
%A Xu, Jun
%A Wang, Gang
%A Dong, Zhenhua
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F ye-etal-2025-q
%X Query rewriting plays a pivotal role in Retrieval-Augmented Generation (RAG) by refining real-world queries of varying complexity. Existing approaches typically rely on outcome-supervised training or heuristic rules to guide the rewriting process. However, these paradigms often struggle to handle queries with varying levels of complexity, posing over- and under-refinement problems. We identify the root cause of these issues as the absence of supervision signals for intermediate steps. To fully construct and utilize such signals, we propose Q-PRM, a novel query rewriting framework. Q-PRM reformulates the rewriting process as a Markov Decision Process (MDP) composed of atomic rewriting steps. In this way, Q-PRM can apply process-level supervision to each atomic step according to the query type, offering more targeted and effective guidance. Q-PRM comprises three key stages: (1) applying Monte Carlo Tree Search to generate step-level process supervision signals; (2) performing reinforced self-training for progressive process refinement; and (3) employing PRM-guided decoding during inference. Experiments on several open-domain QA benchmarks demonstrate that Q-PRM consistently outperforms baselines across different levels of query complexity.
%U https://aclanthology.org/2025.findings-emnlp.817/
%P 15113-15128
Markdown (Informal)
[Q-PRM: Adaptive Query Rewriting for Retrieval-Augmented Generation via Step-level Process Supervision](https://aclanthology.org/2025.findings-emnlp.817/) (Ye et al., Findings 2025)
ACL