@article{nishida-etal-2026-dissecting,
title = "Dissecting {G}raph{RAG}: A Modular Analysis of Knowledge Structuring for Factoid Question Answering",
author = "Nishida, Noriki and
Munne, Rumana Ferdous and
Liu, Shanshan and
Tokunaga, Narumi and
Yamagata, Yuki and
Cheng, Fei and
Kozaki, Kouji and
Matsumoto, Yuji",
journal = "Transactions of the Association for Computational Linguistics",
volume = "14",
year = "2026",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2026.tacl-1.29/",
doi = "10.1162/tacl.a.615",
pages = "627--655",
abstract = "We present a systematic analysis of module-level design choices in GraphRAG, a retrieval-augmented generation framework that integrates structured knowledge graphs into question answering. Focusing on triple extraction, community clustering, and report generation, we evaluate multiple strategies across two knowledge-intensive benchmarks. Our results show that high-quality triple extraction is critical, as the accuracy and coverage of the resulting knowledge graph can become a bottleneck for downstream reasoning. We also find that the granularity of fundamental knowledge units, as determined by community clustering, has a significant impact on downstream performance: Achieving a balance between factual detail and topical coherence within each unit is important to enable precise and comprehensive retrieval and to facilitate effective multi-hop reasoning. In addition, simple template-based reporting outperforms LLM-based summarization in both accuracy and efficiency. These findings provide practical guidance for the structure- aware design of retrieval-augmented systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nishida-etal-2026-dissecting">
<titleInfo>
<title>Dissecting GraphRAG: A Modular Analysis of Knowledge Structuring for Factoid Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Noriki</namePart>
<namePart type="family">Nishida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rumana</namePart>
<namePart type="given">Ferdous</namePart>
<namePart type="family">Munne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shanshan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Narumi</namePart>
<namePart type="family">Tokunaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuki</namePart>
<namePart type="family">Yamagata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kouji</namePart>
<namePart type="family">Kozaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Matsumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>We present a systematic analysis of module-level design choices in GraphRAG, a retrieval-augmented generation framework that integrates structured knowledge graphs into question answering. Focusing on triple extraction, community clustering, and report generation, we evaluate multiple strategies across two knowledge-intensive benchmarks. Our results show that high-quality triple extraction is critical, as the accuracy and coverage of the resulting knowledge graph can become a bottleneck for downstream reasoning. We also find that the granularity of fundamental knowledge units, as determined by community clustering, has a significant impact on downstream performance: Achieving a balance between factual detail and topical coherence within each unit is important to enable precise and comprehensive retrieval and to facilitate effective multi-hop reasoning. In addition, simple template-based reporting outperforms LLM-based summarization in both accuracy and efficiency. These findings provide practical guidance for the structure- aware design of retrieval-augmented systems.</abstract>
<identifier type="citekey">nishida-etal-2026-dissecting</identifier>
<identifier type="doi">10.1162/tacl.a.615</identifier>
<location>
<url>https://aclanthology.org/2026.tacl-1.29/</url>
</location>
<part>
<date>2026</date>
<detail type="volume"><number>14</number></detail>
<extent unit="page">
<start>627</start>
<end>655</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Dissecting GraphRAG: A Modular Analysis of Knowledge Structuring for Factoid Question Answering
%A Nishida, Noriki
%A Munne, Rumana Ferdous
%A Liu, Shanshan
%A Tokunaga, Narumi
%A Yamagata, Yuki
%A Cheng, Fei
%A Kozaki, Kouji
%A Matsumoto, Yuji
%J Transactions of the Association for Computational Linguistics
%D 2026
%V 14
%I MIT Press
%C Cambridge, MA
%F nishida-etal-2026-dissecting
%X We present a systematic analysis of module-level design choices in GraphRAG, a retrieval-augmented generation framework that integrates structured knowledge graphs into question answering. Focusing on triple extraction, community clustering, and report generation, we evaluate multiple strategies across two knowledge-intensive benchmarks. Our results show that high-quality triple extraction is critical, as the accuracy and coverage of the resulting knowledge graph can become a bottleneck for downstream reasoning. We also find that the granularity of fundamental knowledge units, as determined by community clustering, has a significant impact on downstream performance: Achieving a balance between factual detail and topical coherence within each unit is important to enable precise and comprehensive retrieval and to facilitate effective multi-hop reasoning. In addition, simple template-based reporting outperforms LLM-based summarization in both accuracy and efficiency. These findings provide practical guidance for the structure- aware design of retrieval-augmented systems.
%R 10.1162/tacl.a.615
%U https://aclanthology.org/2026.tacl-1.29/
%U https://doi.org/10.1162/tacl.a.615
%P 627-655
Markdown (Informal)
[Dissecting GraphRAG: A Modular Analysis of Knowledge Structuring for Factoid Question Answering](https://aclanthology.org/2026.tacl-1.29/) (Nishida et al., TACL 2026)
ACL