Span-Based Reasoning with Anonymous Knowledge Graphs

Daniel Guzman Olivares; Lara Quijano; Federico Liberatore

Span-Based Reasoning with Anonymous Knowledge Graphs

Daniel Guzman Olivares, Lara Quijano, Federico Liberatore

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

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>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

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

Modern KGQA pipelines address complex multi-hop reasoning by shifting retrieval from classical embedding-based methods to iterative LLM calls. Although effective, this incurs significant computational and economic overhead that limits their applicability in real-world settings. In this paper, we introduce GRASE (Graph Reasoning with Anonymous Span Encoders), a framework that replaces LLM-driven search with a novel encoder-based graph-span representations over uncertain nodes and relations in a knowledge graph. Across several multi-hop KGQA benchmark datasets, GRASE achieves up to 85% faster inference than LLM-native pipelines while matching or exceeding state-of-the-art performance, demonstrating that encoder-only hybrid reasoning is a robust, practical, and scalable alternative to fully LLM-driven retrieval.

Anthology ID:: 2026.emnlp-main.1767
Volume:: Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Hung-Yi Lee, Sunipa Dev, Jessy Li, Desmond Elliott
Venue:: EMNLP
SIG:: SIGDAT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 40283–40303
Language:
URL:: https://aclanthology.org/2026.emnlp-main.1767/
DOI:
Bibkey:
Cite (ACL):: Daniel Guzman Olivares, Lara Quijano, and Federico Liberatore. 2026. Span-Based Reasoning with Anonymous Knowledge Graphs. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 40283–40303, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: Span-Based Reasoning with Anonymous Knowledge Graphs (Guzman Olivares et al., EMNLP 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.emnlp-main.1767.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{guzman-olivares-etal-2026-span,
    title = "Span-Based Reasoning with Anonymous Knowledge Graphs",
    author = "Guzman Olivares, Daniel  and
      Quijano, Lara  and
      Liberatore, Federico",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.1767/",
    pages = "40283--40303",
    ISBN = "979-8-89176-459-0",
    abstract = "Modern KGQA pipelines address complex multi-hop reasoning by shifting retrieval from classical embedding-based methods to iterative LLM calls. Although effective, this incurs significant computational and economic overhead that limits their applicability in real-world settings. In this paper, we introduce GRASE (Graph Reasoning with Anonymous Span Encoders), a framework that replaces LLM-driven search with a novel encoder-based graph-span representations over uncertain nodes and relations in a knowledge graph. Across several multi-hop KGQA benchmark datasets, GRASE achieves up to 85{\%} faster inference than LLM-native pipelines while matching or exceeding state-of-the-art performance, demonstrating that encoder-only hybrid reasoning is a robust, practical, and scalable alternative to fully LLM-driven retrieval."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guzman-olivares-etal-2026-span">
    <titleInfo>
        <title>Span-Based Reasoning with Anonymous Knowledge Graphs</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Daniel</namePart>
        <namePart type="family">Guzman Olivares</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lara</namePart>
        <namePart type="family">Quijano</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Federico</namePart>
        <namePart type="family">Liberatore</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Modern KGQA pipelines address complex multi-hop reasoning by shifting retrieval from classical embedding-based methods to iterative LLM calls. Although effective, this incurs significant computational and economic overhead that limits their applicability in real-world settings. In this paper, we introduce GRASE (Graph Reasoning with Anonymous Span Encoders), a framework that replaces LLM-driven search with a novel encoder-based graph-span representations over uncertain nodes and relations in a knowledge graph. Across several multi-hop KGQA benchmark datasets, GRASE achieves up to 85% faster inference than LLM-native pipelines while matching or exceeding state-of-the-art performance, demonstrating that encoder-only hybrid reasoning is a robust, practical, and scalable alternative to fully LLM-driven retrieval.</abstract>
    <identifier type="citekey">guzman-olivares-etal-2026-span</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1767/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>40283</start>
            <end>40303</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Span-Based Reasoning with Anonymous Knowledge Graphs
%A Guzman Olivares, Daniel
%A Quijano, Lara
%A Liberatore, Federico
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F guzman-olivares-etal-2026-span
%X Modern KGQA pipelines address complex multi-hop reasoning by shifting retrieval from classical embedding-based methods to iterative LLM calls. Although effective, this incurs significant computational and economic overhead that limits their applicability in real-world settings. In this paper, we introduce GRASE (Graph Reasoning with Anonymous Span Encoders), a framework that replaces LLM-driven search with a novel encoder-based graph-span representations over uncertain nodes and relations in a knowledge graph. Across several multi-hop KGQA benchmark datasets, GRASE achieves up to 85% faster inference than LLM-native pipelines while matching or exceeding state-of-the-art performance, demonstrating that encoder-only hybrid reasoning is a robust, practical, and scalable alternative to fully LLM-driven retrieval.
%U https://aclanthology.org/2026.emnlp-main.1767/
%P 40283-40303

Download as File

Markdown (Informal)

[Span-Based Reasoning with Anonymous Knowledge Graphs](https://aclanthology.org/2026.emnlp-main.1767/) (Guzman Olivares et al., EMNLP 2026)

Span-Based Reasoning with Anonymous Knowledge Graphs (Guzman Olivares et al., EMNLP 2026)

ACL

Daniel Guzman Olivares, Lara Quijano, and Federico Liberatore. 2026. Span-Based Reasoning with Anonymous Knowledge Graphs. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 40283–40303, Budapest, Hungary. Association for Computational Linguistics.