<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-stride">
    <titleInfo>
        <title>STRIDE: Structural Reasoning for In-context Demonstration Extraction in Multi-hop Question Answering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shiwei</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bin</namePart>
        <namePart type="family">Liang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yue</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kam-Fai</namePart>
        <namePart type="family">Wong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hui</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ruifeng</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruifeng</namePart>
            <namePart type="family">Xu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ayu</namePart>
            <namePart type="family">Purwarianti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tong</namePart>
            <namePart type="family">Rong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jun</namePart>
            <namePart type="family">Suzuki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hengqin, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-439-2</identifier>
    </relatedItem>
    <abstract>In-context learning (ICL) for multi-hop question answering (MHQA) depends critically on the choice of demonstrations. Yet most existing methods prioritize semantic similarity, even though semantically similar examples may follow different reasoning paths and therefore be poor demonstrations for the target query. We present STRIDE (STructural Reasoning for In-context Demonstration Extraction), a structure-centric framework for multi-hop QA. STRIDE first infers the latent reasoning structure of a query. It then performs positive–contrastive structural routing, selecting structurally compatible demonstrations as positives and semantically plausible but structurally mismatched examples as contrastives. Finally, it constructs structural prompts that expose compact, role-consistent reasoning traces over supporting evidence. Together, it turns demonstration retrieval from semantic matching into structure-aware problem-solving guidance. Empirical results show that STRIDE consistently improves downstream QA performance across settings.</abstract>
    <identifier type="citekey">chen-etal-2026-stride</identifier>
    <location>
        <url>https://aclanthology.org/2026.aacl-long.181/</url>
    </location>
    <part>
        <date>2026-11</date>
        <extent unit="page">
            <start>4035</start>
            <end>4056</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T STRIDE: Structural Reasoning for In-context Demonstration Extraction in Multi-hop Question Answering
%A Chen, Shiwei
%A Liang, Bin
%A Yu, Yue
%A Wong, Kam-Fai
%A Wang, Hui
%A Xu, Ruifeng
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F chen-etal-2026-stride
%X In-context learning (ICL) for multi-hop question answering (MHQA) depends critically on the choice of demonstrations. Yet most existing methods prioritize semantic similarity, even though semantically similar examples may follow different reasoning paths and therefore be poor demonstrations for the target query. We present STRIDE (STructural Reasoning for In-context Demonstration Extraction), a structure-centric framework for multi-hop QA. STRIDE first infers the latent reasoning structure of a query. It then performs positive–contrastive structural routing, selecting structurally compatible demonstrations as positives and semantically plausible but structurally mismatched examples as contrastives. Finally, it constructs structural prompts that expose compact, role-consistent reasoning traces over supporting evidence. Together, it turns demonstration retrieval from semantic matching into structure-aware problem-solving guidance. Empirical results show that STRIDE consistently improves downstream QA performance across settings.
%U https://aclanthology.org/2026.aacl-long.181/
%P 4035-4056

Markdown (Informal)

[STRIDE: Structural Reasoning for In-context Demonstration Extraction in Multi-hop Question Answering](https://aclanthology.org/2026.aacl-long.181/) (Chen et al., AACL-IJCNLP 2026)

• STRIDE: Structural Reasoning for In-context Demonstration Extraction in Multi-hop Question Answering (Chen et al., AACL-IJCNLP 2026)

ACL

• Shiwei Chen, Bin Liang, Yue Yu, Kam-Fai Wong, Hui Wang, and Ruifeng Xu. 2026. STRIDE: Structural Reasoning for In-context Demonstration Extraction in Multi-hop Question Answering. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4035–4056, Hengqin, China. Association for Computational Linguistics.