<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vanmechelen-etal-2026-quantifying">
    <titleInfo>
        <title>Quantifying Retrieval Quality in GraphRAG: A Schema-Agnostic Approach</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Thibaud</namePart>
        <namePart type="family">Vanmechelen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexandre</namePart>
        <namePart type="family">Achten</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zaineb</namePart>
        <namePart type="family">Gabsi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sabri</namePart>
        <namePart type="family">Skhiri</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>While LLMs have achieved significant success in natural language tasks, their tendency to hallucinate remains a critical challenge. RAG tries to address this issue by grounding models in external data; however, standard vector-based RAGs often fail when working with highly interconnected datasets. GraphRAG has emerged as a superior alternative in this setting by modelling the relational topology, yet evaluating GraphRAGs remains challenging. Current benchmarks predominantly focus on the final LLM-generated output frequently overlooking the structural accuracy of the underlying retrieval process. In this paper, we propose a novel schema-agnostic framework for the automated generation of synthetic evaluation datasets from KGs. Unlike previous approaches, our framework establishes a rigorous, deterministic ground truth to specifically quantify the retriever performance across nine distinct query categories, including multi-hop and aggregation tasks. We demonstrate the utility of this benchmark by applying it to a biochemical KG and evaluating four diverse retrieval architectures. Our results indicate that agentic, LLM-driven retrievers provide the highest recall and reasoning capacity, effectively navigating complex topologies where other methods struggle. This work provides a robust, scalable methodology for performance tracking, shifting the evaluation of GraphRAG toward a more topologically precise standard.</abstract>
    <identifier type="citekey">vanmechelen-etal-2026-quantifying</identifier>
    <identifier type="doi">10.63317/5h4oct2t73a2</identifier>
    <location>
        <url>https://aclanthology.org/2026.kallm-1.18/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>176</start>
            <end>189</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Quantifying Retrieval Quality in GraphRAG: A Schema-Agnostic Approach
%A Vanmechelen, Thibaud
%A Achten, Alexandre
%A Gabsi, Zaineb
%A Skhiri, Sabri
%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 vanmechelen-etal-2026-quantifying
%X While LLMs have achieved significant success in natural language tasks, their tendency to hallucinate remains a critical challenge. RAG tries to address this issue by grounding models in external data; however, standard vector-based RAGs often fail when working with highly interconnected datasets. GraphRAG has emerged as a superior alternative in this setting by modelling the relational topology, yet evaluating GraphRAGs remains challenging. Current benchmarks predominantly focus on the final LLM-generated output frequently overlooking the structural accuracy of the underlying retrieval process. In this paper, we propose a novel schema-agnostic framework for the automated generation of synthetic evaluation datasets from KGs. Unlike previous approaches, our framework establishes a rigorous, deterministic ground truth to specifically quantify the retriever performance across nine distinct query categories, including multi-hop and aggregation tasks. We demonstrate the utility of this benchmark by applying it to a biochemical KG and evaluating four diverse retrieval architectures. Our results indicate that agentic, LLM-driven retrievers provide the highest recall and reasoning capacity, effectively navigating complex topologies where other methods struggle. This work provides a robust, scalable methodology for performance tracking, shifting the evaluation of GraphRAG toward a more topologically precise standard.
%R 10.63317/5h4oct2t73a2
%U https://aclanthology.org/2026.kallm-1.18/
%U https://doi.org/10.63317/5h4oct2t73a2
%P 176-189

Markdown (Informal)

[Quantifying Retrieval Quality in GraphRAG: A Schema-Agnostic Approach](https://aclanthology.org/2026.kallm-1.18/) (Vanmechelen et al., KaLLM 2026)

• Quantifying Retrieval Quality in GraphRAG: A Schema-Agnostic Approach (Vanmechelen et al., KaLLM 2026)

ACL

• Thibaud Vanmechelen, Alexandre Achten, Zaineb Gabsi, and Sabri Skhiri. 2026. Quantifying Retrieval Quality in GraphRAG: A Schema-Agnostic Approach. In Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26, pages 176–189, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).