<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2026-beyond-static">
    <titleInfo>
        <title>Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kai</namePart>
        <namePart type="family">Guo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xinnan</namePart>
        <namePart type="family">Dai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shenglai</namePart>
        <namePart type="family">Zeng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Harry</namePart>
        <namePart type="family">Shomer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Haoyu</namePart>
        <namePart type="family">Han</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yu</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hui</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Graph-based RAG (GraphRAG) leverages entity–relation graphs to support multi-hop reasoning, but most systems still rely on static retrieval. When crucial evidence, especially bridge documents that connect disjoint entities, is absent, reasoning collapses and hallucinations persist. Iterative retrieval, which performs multiple rounds of evidence selection, has emerged as a promising alternative, yet its role within GraphRAG remains poorly understood. We present the first systematic study of iterative retrieval in GraphRAG by analyzing how different strategies interact with graph-based backbones and investigating when they are effective. Our findings reveal both opportunities and pitfalls which together highlight a central bottleneck, namely that GraphRAG’s effectiveness depends not only on recall but also on whether bridge evidence is consistently promoted into leading positions where it can support reasoning chains. To address this limitation, we propose Bridge-Guided Dual-Thought-based Retrieval (BDTR), a simple yet effective framework that generates complementary thoughts and leverages reasoning chains to recalibrate rankings and bring bridge evidence into leading positions. BDTR achieves consistent improvements across diverse GraphRAG settings and provides guidance for the design of future GraphRAG systems. Our code is available at https://github.com/KaiGuo20/BDTR.</abstract>
    <identifier type="citekey">guo-etal-2026-beyond-static</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1897/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>43249</start>
            <end>43271</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG
%A Guo, Kai
%A Dai, Xinnan
%A Zeng, Shenglai
%A Shomer, Harry
%A Han, Haoyu
%A Wang, Yu
%A Liu, Hui
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F guo-etal-2026-beyond-static
%X Graph-based RAG (GraphRAG) leverages entity–relation graphs to support multi-hop reasoning, but most systems still rely on static retrieval. When crucial evidence, especially bridge documents that connect disjoint entities, is absent, reasoning collapses and hallucinations persist. Iterative retrieval, which performs multiple rounds of evidence selection, has emerged as a promising alternative, yet its role within GraphRAG remains poorly understood. We present the first systematic study of iterative retrieval in GraphRAG by analyzing how different strategies interact with graph-based backbones and investigating when they are effective. Our findings reveal both opportunities and pitfalls which together highlight a central bottleneck, namely that GraphRAG’s effectiveness depends not only on recall but also on whether bridge evidence is consistently promoted into leading positions where it can support reasoning chains. To address this limitation, we propose Bridge-Guided Dual-Thought-based Retrieval (BDTR), a simple yet effective framework that generates complementary thoughts and leverages reasoning chains to recalibrate rankings and bring bridge evidence into leading positions. BDTR achieves consistent improvements across diverse GraphRAG settings and provides guidance for the design of future GraphRAG systems. Our code is available at https://github.com/KaiGuo20/BDTR.
%U https://aclanthology.org/2026.emnlp-main.1897/
%P 43249-43271

Markdown (Informal)

[Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG](https://aclanthology.org/2026.emnlp-main.1897/) (Guo et al., EMNLP 2026)

• Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG (Guo et al., EMNLP 2026)

ACL

• Kai Guo, Xinnan Dai, Shenglai Zeng, Harry Shomer, Haoyu Han, Yu Wang, and Hui Liu. 2026. Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 43249–43271, Budapest, Hungary. Association for Computational Linguistics.