<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="davidsson-harmouch-2026-end">
    <titleInfo>
        <title>End-to-End Graph Retrieval Pipeline for Specialized Domains</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Haraldur</namePart>
        <namePart type="family">Davidsson</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hazar</namePart>
        <namePart type="family">Harmouch</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>We present an end-to-end pipeline for constructing a domain-specific knowledge graph from instructional text using Large Language Model assisted extraction. Applied to the Icelandic Riding Levels, a 602 pages training corpus for riders of the Icelandic Horse, the pipeline produces a hyper-relational knowledge graph of 9,382 nodes and 16,423 edges, where schema-constrained qualifiers preserve the conditional and procedural context that standard triples discard. To evaluate the resulting graph, we introduce the first expert validated question answering benchmark for this domain: 252 questions across four reasoning categories. Comparing Graph-, Text-, and Hybrid-retrieval augmented generation methods, we find that Text-based achieves the highest overall accuracy, but that Graph-based provides the only correct answer for a subset of queries, particularly where the corpus contains competing values for the same fact. A failure analysis traces the majority of Graph-based retrieval errors to context dilution at high-degree hub nodes, an algorithmic limitation in graph traversal. We discuss implications for adaptive retrieval strategies that route queries to the appropriate modality.</abstract>
    <identifier type="citekey">davidsson-harmouch-2026-end</identifier>
    <identifier type="doi">10.63317/3xjhui2zyiws</identifier>
    <location>
        <url>https://aclanthology.org/2026.kallm-1.16/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>155</start>
            <end>165</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T End-to-End Graph Retrieval Pipeline for Specialized Domains
%A Davidsson, Haraldur
%A Harmouch, Hazar
%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 davidsson-harmouch-2026-end
%X We present an end-to-end pipeline for constructing a domain-specific knowledge graph from instructional text using Large Language Model assisted extraction. Applied to the Icelandic Riding Levels, a 602 pages training corpus for riders of the Icelandic Horse, the pipeline produces a hyper-relational knowledge graph of 9,382 nodes and 16,423 edges, where schema-constrained qualifiers preserve the conditional and procedural context that standard triples discard. To evaluate the resulting graph, we introduce the first expert validated question answering benchmark for this domain: 252 questions across four reasoning categories. Comparing Graph-, Text-, and Hybrid-retrieval augmented generation methods, we find that Text-based achieves the highest overall accuracy, but that Graph-based provides the only correct answer for a subset of queries, particularly where the corpus contains competing values for the same fact. A failure analysis traces the majority of Graph-based retrieval errors to context dilution at high-degree hub nodes, an algorithmic limitation in graph traversal. We discuss implications for adaptive retrieval strategies that route queries to the appropriate modality.
%R 10.63317/3xjhui2zyiws
%U https://aclanthology.org/2026.kallm-1.16/
%U https://doi.org/10.63317/3xjhui2zyiws
%P 155-165

Markdown (Informal)

[End-to-End Graph Retrieval Pipeline for Specialized Domains](https://aclanthology.org/2026.kallm-1.16/) (Davidsson & Harmouch, KaLLM 2026)

• End-to-End Graph Retrieval Pipeline for Specialized Domains (Davidsson & Harmouch, KaLLM 2026)

ACL

• Haraldur Davidsson and Hazar Harmouch. 2026. End-to-End Graph Retrieval Pipeline for Specialized Domains. In Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26, pages 155–165, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).