@inproceedings{karkout-etal-2026-efficient,
title = "Efficient {KG}-Augmented {RAG} with Reusable Graph Community Summaries",
author = "Karkout, Maha and
Khodorchenko, Maria Andreevna and
Butakov, Nikolay Alekseevich and
Nasonov, Denis",
editor = "S{\'e}rasset, Gilles and
Gkirtzou, Katerina and
Cochez, Michael and
Kalo, Jan-Christoph",
booktitle = "Proceedings of the Knowledge Graphs and Large Language Models Workshop ({KG}-{LLM}) @ {LREC}26",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.kallm-1.12/",
doi = "10.63317/5fibrr6chehg",
pages = "110--119",
abstract = "Retrieval-augmented generation (RAG) performs well for localized factual queries but struggles with complex questions requiring multi-section evidence integration. Graph-based approaches introduce relational structure, yet their practical integration into QA pipelines involves significant query-time overhead. We present a practical KG-augmented RAG (KG-RAG) design that builds a knowledge graph offline with an LLM, converts graph communities into reusable summaries, and retrieves these summaries jointly with textual evidence at query time. We compare dense RAG, pure GraphRAG, and the proposed hybrid on two benchmarks representing complementary retrieval paradigms: QASPER (intra-document reasoning over scientific papers) and ObliQA (cross-document reasoning over regulatory texts). Results show that pure GraphRAG does not consistently outperform dense retrieval, whereas the hybrid configuration systematically improves relevance, correctness, and completeness while maintaining substantially lower latency than full graph-based inference."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="karkout-etal-2026-efficient">
<titleInfo>
<title>Efficient KG-Augmented RAG with Reusable Graph Community Summaries</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maha</namePart>
<namePart type="family">Karkout</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Andreevna</namePart>
<namePart type="family">Khodorchenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolay</namePart>
<namePart type="given">Alekseevich</namePart>
<namePart type="family">Butakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Denis</namePart>
<namePart type="family">Nasonov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gilles</namePart>
<namePart type="family">Sérasset</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katerina</namePart>
<namePart type="family">Gkirtzou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Cochez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan-Christoph</namePart>
<namePart type="family">Kalo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Retrieval-augmented generation (RAG) performs well for localized factual queries but struggles with complex questions requiring multi-section evidence integration. Graph-based approaches introduce relational structure, yet their practical integration into QA pipelines involves significant query-time overhead. We present a practical KG-augmented RAG (KG-RAG) design that builds a knowledge graph offline with an LLM, converts graph communities into reusable summaries, and retrieves these summaries jointly with textual evidence at query time. We compare dense RAG, pure GraphRAG, and the proposed hybrid on two benchmarks representing complementary retrieval paradigms: QASPER (intra-document reasoning over scientific papers) and ObliQA (cross-document reasoning over regulatory texts). Results show that pure GraphRAG does not consistently outperform dense retrieval, whereas the hybrid configuration systematically improves relevance, correctness, and completeness while maintaining substantially lower latency than full graph-based inference.</abstract>
<identifier type="citekey">karkout-etal-2026-efficient</identifier>
<identifier type="doi">10.63317/5fibrr6chehg</identifier>
<location>
<url>https://aclanthology.org/2026.kallm-1.12/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>110</start>
<end>119</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient KG-Augmented RAG with Reusable Graph Community Summaries
%A Karkout, Maha
%A Khodorchenko, Maria Andreevna
%A Butakov, Nikolay Alekseevich
%A Nasonov, Denis
%Y Sérasset, Gilles
%Y Gkirtzou, Katerina
%Y Cochez, Michael
%Y Kalo, Jan-Christoph
%S Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F karkout-etal-2026-efficient
%X Retrieval-augmented generation (RAG) performs well for localized factual queries but struggles with complex questions requiring multi-section evidence integration. Graph-based approaches introduce relational structure, yet their practical integration into QA pipelines involves significant query-time overhead. We present a practical KG-augmented RAG (KG-RAG) design that builds a knowledge graph offline with an LLM, converts graph communities into reusable summaries, and retrieves these summaries jointly with textual evidence at query time. We compare dense RAG, pure GraphRAG, and the proposed hybrid on two benchmarks representing complementary retrieval paradigms: QASPER (intra-document reasoning over scientific papers) and ObliQA (cross-document reasoning over regulatory texts). Results show that pure GraphRAG does not consistently outperform dense retrieval, whereas the hybrid configuration systematically improves relevance, correctness, and completeness while maintaining substantially lower latency than full graph-based inference.
%R 10.63317/5fibrr6chehg
%U https://aclanthology.org/2026.kallm-1.12/
%U https://doi.org/10.63317/5fibrr6chehg
%P 110-119
Markdown (Informal)
[Efficient KG-Augmented RAG with Reusable Graph Community Summaries](https://aclanthology.org/2026.kallm-1.12/) (Karkout et al., KaLLM 2026)
ACL
- Maha Karkout, Maria Andreevna Khodorchenko, Nikolay Alekseevich Butakov, and Denis Nasonov. 2026. Efficient KG-Augmented RAG with Reusable Graph Community Summaries. In Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26, pages 110–119, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).