<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qin-etal-2025-reinforced">
    <titleInfo>
        <title>Reinforced Query Reasoners for Reasoning-intensive Retrieval Tasks</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xubo</namePart>
        <namePart type="family">Qin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jun</namePart>
        <namePart type="family">Bai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiaqi</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zixia</namePart>
        <namePart type="family">Jia</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zilong</namePart>
        <namePart type="family">Zheng</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>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-332-6</identifier>
    </relatedItem>
    <abstract>Traditional information retrieval (IR) methods excel at textual and semantic matching but struggle in reasoning-intensive retrieval tasks that require multi-hop inference or complex semantic understanding between queries and documents. One promising solution is to explicitly rewrite or augment queries using large language models (LLMs) to elicit reasoning-relevant content prior to retrieval. However, the widespread use of large-scale LLMs like GPT-4 or LLaMA3-70B remains impractical due to their high inference cost and limited deployability in real-world systems. In this work, we introduce Reinforced Query Reasoner (RQR), a family of small-scale language models for query reasoning and rewriting in reasoning-intensive retrieval. Our approach frames query reformulation as a reinforcement learning problem and employs a novel semi-rule-based reward function. This enables smaller language models, e.g., Qwen2.5-7B-Instruct and Qwen2.5-1.5B-Instruct, to achieve reasoning performance rivaling large-scale LLMs without their prohibitive inference costs. Experiment results on BRIGHT benchmark show that, with BM25 as retrievers, both RQR-7B and RQR-1.5B models significantly outperform existing baselines, including prompt-based query reasoners and some latest dense retrievers trained for reasoning-intensive retrieval tasks, offering superior adaptability for real-world deployment. All code and dataset will be publicly released.</abstract>
    <identifier type="citekey">qin-etal-2025-reinforced</identifier>
    <location>
        <url>https://aclanthology.org/2025.emnlp-main.1078/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>21261</start>
            <end>21274</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Reinforced Query Reasoners for Reasoning-intensive Retrieval Tasks
%A Qin, Xubo
%A Bai, Jun
%A Li, Jiaqi
%A Jia, Zixia
%A Zheng, Zilong
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F qin-etal-2025-reinforced
%X Traditional information retrieval (IR) methods excel at textual and semantic matching but struggle in reasoning-intensive retrieval tasks that require multi-hop inference or complex semantic understanding between queries and documents. One promising solution is to explicitly rewrite or augment queries using large language models (LLMs) to elicit reasoning-relevant content prior to retrieval. However, the widespread use of large-scale LLMs like GPT-4 or LLaMA3-70B remains impractical due to their high inference cost and limited deployability in real-world systems. In this work, we introduce Reinforced Query Reasoner (RQR), a family of small-scale language models for query reasoning and rewriting in reasoning-intensive retrieval. Our approach frames query reformulation as a reinforcement learning problem and employs a novel semi-rule-based reward function. This enables smaller language models, e.g., Qwen2.5-7B-Instruct and Qwen2.5-1.5B-Instruct, to achieve reasoning performance rivaling large-scale LLMs without their prohibitive inference costs. Experiment results on BRIGHT benchmark show that, with BM25 as retrievers, both RQR-7B and RQR-1.5B models significantly outperform existing baselines, including prompt-based query reasoners and some latest dense retrievers trained for reasoning-intensive retrieval tasks, offering superior adaptability for real-world deployment. All code and dataset will be publicly released.
%U https://aclanthology.org/2025.emnlp-main.1078/
%P 21261-21274

Markdown (Informal)

[Reinforced Query Reasoners for Reasoning-intensive Retrieval Tasks](https://aclanthology.org/2025.emnlp-main.1078/) (Qin et al., EMNLP 2025)

• Reinforced Query Reasoners for Reasoning-intensive Retrieval Tasks (Qin et al., EMNLP 2025)

ACL

• Xubo Qin, Jun Bai, Jiaqi Li, Zixia Jia, and Zilong Zheng. 2025. Reinforced Query Reasoners for Reasoning-intensive Retrieval Tasks. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 21261–21274, Suzhou, China. Association for Computational Linguistics.