Retrieving Relevant Knowledge Subgraphs for Task-Oriented Dialogue

Nicholas Thomas Walker; Pierre Lison; Laetitia Hilgendorf; Nicolas Wagner; Stefan Ultes

Retrieving Relevant Knowledge Subgraphs for Task-Oriented Dialogue

Nicholas Thomas Walker, Pierre Lison, Laetitia Hilgendorf, Nicolas Wagner, Stefan Ultes

Correct Metadata for

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

In this paper, we present an approach for extracting knowledge graph information for retrieval augmented generation in dialogue systems. Knowledge graphs are a rich source of background information, but the inclusion of more potentially useful information in a system prompt risks decreased model performance from excess context. We investigate a method of retrieving relevant subgraphs of maximum relevance and minimum size by framing this trade-off as a Prize-collecting Steiner Tree problem. The results of our user study and analysis indicate promising efficacy of a simple subgraph retrieval approach compared with a top-K retrieval model.

Anthology ID:: 2025.sigdial-1.42
Volume:: Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:: August
Year:: 2025
Address:: Avignon, France
Editors:: Frédéric Béchet, Fabrice Lefèvre, Nicholas Asher, Seokhwan Kim, Teva Merlin
Venue:: SIGDIAL
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 513–526
Language:
URL:: https://aclanthology.org/2025.sigdial-1.42/
DOI:
Bibkey:
Cite (ACL):: Nicholas Thomas Walker, Pierre Lison, Laetitia Hilgendorf, Nicolas Wagner, and Stefan Ultes. 2025. Retrieving Relevant Knowledge Subgraphs for Task-Oriented Dialogue. In Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 513–526, Avignon, France. Association for Computational Linguistics.
Cite (Informal):: Retrieving Relevant Knowledge Subgraphs for Task-Oriented Dialogue (Walker et al., SIGDIAL 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.sigdial-1.42.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{walker-etal-2025-retrieving,
    title = "Retrieving Relevant Knowledge Subgraphs for Task-Oriented Dialogue",
    author = "Walker, Nicholas Thomas  and
      Lison, Pierre  and
      Hilgendorf, Laetitia  and
      Wagner, Nicolas  and
      Ultes, Stefan",
    editor = "B{\'e}chet, Fr{\'e}d{\'e}ric  and
      Lef{\`e}vre, Fabrice  and
      Asher, Nicholas  and
      Kim, Seokhwan  and
      Merlin, Teva",
    booktitle = "Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
    month = aug,
    year = "2025",
    address = "Avignon, France",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.sigdial-1.42/",
    pages = "513--526",
    abstract = "In this paper, we present an approach for extracting knowledge graph information for retrieval augmented generation in dialogue systems. Knowledge graphs are a rich source of background information, but the inclusion of more potentially useful information in a system prompt risks decreased model performance from excess context. We investigate a method of retrieving relevant subgraphs of maximum relevance and minimum size by framing this trade-off as a Prize-collecting Steiner Tree problem. The results of our user study and analysis indicate promising efficacy of a simple subgraph retrieval approach compared with a top-K retrieval model."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="walker-etal-2025-retrieving">
    <titleInfo>
        <title>Retrieving Relevant Knowledge Subgraphs for Task-Oriented Dialogue</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nicholas</namePart>
        <namePart type="given">Thomas</namePart>
        <namePart type="family">Walker</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pierre</namePart>
        <namePart type="family">Lison</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Laetitia</namePart>
        <namePart type="family">Hilgendorf</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nicolas</namePart>
        <namePart type="family">Wagner</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Stefan</namePart>
        <namePart type="family">Ultes</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Frédéric</namePart>
            <namePart type="family">Béchet</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Fabrice</namePart>
            <namePart type="family">Lefèvre</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nicholas</namePart>
            <namePart type="family">Asher</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Seokhwan</namePart>
            <namePart type="family">Kim</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Teva</namePart>
            <namePart type="family">Merlin</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Avignon, France</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper, we present an approach for extracting knowledge graph information for retrieval augmented generation in dialogue systems. Knowledge graphs are a rich source of background information, but the inclusion of more potentially useful information in a system prompt risks decreased model performance from excess context. We investigate a method of retrieving relevant subgraphs of maximum relevance and minimum size by framing this trade-off as a Prize-collecting Steiner Tree problem. The results of our user study and analysis indicate promising efficacy of a simple subgraph retrieval approach compared with a top-K retrieval model.</abstract>
    <identifier type="citekey">walker-etal-2025-retrieving</identifier>
    <location>
        <url>https://aclanthology.org/2025.sigdial-1.42/</url>
    </location>
    <part>
        <date>2025-08</date>
        <extent unit="page">
            <start>513</start>
            <end>526</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Retrieving Relevant Knowledge Subgraphs for Task-Oriented Dialogue
%A Walker, Nicholas Thomas
%A Lison, Pierre
%A Hilgendorf, Laetitia
%A Wagner, Nicolas
%A Ultes, Stefan
%Y Béchet, Frédéric
%Y Lefèvre, Fabrice
%Y Asher, Nicholas
%Y Kim, Seokhwan
%Y Merlin, Teva
%S Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2025
%8 August
%I Association for Computational Linguistics
%C Avignon, France
%F walker-etal-2025-retrieving
%X In this paper, we present an approach for extracting knowledge graph information for retrieval augmented generation in dialogue systems. Knowledge graphs are a rich source of background information, but the inclusion of more potentially useful information in a system prompt risks decreased model performance from excess context. We investigate a method of retrieving relevant subgraphs of maximum relevance and minimum size by framing this trade-off as a Prize-collecting Steiner Tree problem. The results of our user study and analysis indicate promising efficacy of a simple subgraph retrieval approach compared with a top-K retrieval model.
%U https://aclanthology.org/2025.sigdial-1.42/
%P 513-526

Download as File

Markdown (Informal)

[Retrieving Relevant Knowledge Subgraphs for Task-Oriented Dialogue](https://aclanthology.org/2025.sigdial-1.42/) (Walker et al., SIGDIAL 2025)

Retrieving Relevant Knowledge Subgraphs for Task-Oriented Dialogue (Walker et al., SIGDIAL 2025)

ACL

Nicholas Thomas Walker, Pierre Lison, Laetitia Hilgendorf, Nicolas Wagner, and Stefan Ultes. 2025. Retrieving Relevant Knowledge Subgraphs for Task-Oriented Dialogue. In Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 513–526, Avignon, France. Association for Computational Linguistics.