Trust the Query, Not the Answer: Auditable Text-to-SPARQL over the GLEIF Register

Jannic Alexander Cutura

Trust the Query, Not the Answer: Auditable Text-to-SPARQL over the GLEIF Register

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

Ask which subsidiaries a conglomerate owns, and a language model returns a plausible list, unverifiable and partly wrong; in compliance or supervision, that will not do. So instead of trusting the answer, a local open-weight model translates each question into an auditable SPARQL query over the GLEIF register, returning the query and its source records. A 20B model answers 86.7% of held-out questions correctly, always with a valid query and declining the unanswerable, and no larger open or closed model does better. The method fits any ontology-described source; code and benchmark are released.

Anthology ID:: 2026.finnlp-1.9
Volume:: Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Jimin Huang, Yongjae Lee, Sophia Ananiadou, Hsin-Hsi Chen, Hiroya Takamura, Chung-Chi Chen
Venues:: FinNLP | WS
SIG:: SIGFinTech
Publisher:: Association for Computational Linguistics
Note:
Pages:: 91–97
Language:
URL:: https://aclanthology.org/2026.finnlp-1.9/
DOI:
Bibkey:
Cite (ACL):: Jannic Alexander Cutura. 2026. Trust the Query, Not the Answer: Auditable Text-to-SPARQL over the GLEIF Register. In Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing, pages 91–97, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: Trust the Query, Not the Answer: Auditable Text-to-SPARQL over the GLEIF Register (Cutura, FinNLP 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.finnlp-1.9.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{cutura-2026-trust,
    title = "Trust the Query, Not the Answer: Auditable Text-to-{SPARQL} over the {GLEIF} Register",
    author = "Cutura, Jannic Alexander",
    editor = "Huang, Jimin  and
      Lee, Yongjae  and
      Ananiadou, Sophia  and
      Chen, Hsin-Hsi  and
      Takamura, Hiroya  and
      Chen, Chung-Chi",
    booktitle = "Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.finnlp-1.9/",
    pages = "91--97",
    ISBN = "979-8-89176-466-8",
    abstract = "Ask which subsidiaries a conglomerate owns, and a language model returns a plausible list, unverifiable and partly wrong; in compliance or supervision, that will not do. So instead of trusting the answer, a local open-weight model translates each question into an auditable SPARQL query over the GLEIF register, returning the query and its source records. A 20B model answers 86.7{\%} of held-out questions correctly, always with a valid query and declining the unanswerable, and no larger open or closed model does better. The method fits any ontology-described source; code and benchmark are released."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cutura-2026-trust">
    <titleInfo>
        <title>Trust the Query, Not the Answer: Auditable Text-to-SPARQL over the GLEIF Register</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jannic</namePart>
        <namePart type="given">Alexander</namePart>
        <namePart type="family">Cutura</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 11th Workshop on Financial Technology and Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Jimin</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yongjae</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sophia</namePart>
            <namePart type="family">Ananiadou</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hsin-Hsi</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hiroya</namePart>
            <namePart type="family">Takamura</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Chung-Chi</namePart>
            <namePart type="family">Chen</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">979-8-89176-466-8</identifier>
    </relatedItem>
    <abstract>Ask which subsidiaries a conglomerate owns, and a language model returns a plausible list, unverifiable and partly wrong; in compliance or supervision, that will not do. So instead of trusting the answer, a local open-weight model translates each question into an auditable SPARQL query over the GLEIF register, returning the query and its source records. A 20B model answers 86.7% of held-out questions correctly, always with a valid query and declining the unanswerable, and no larger open or closed model does better. The method fits any ontology-described source; code and benchmark are released.</abstract>
    <identifier type="citekey">cutura-2026-trust</identifier>
    <location>
        <url>https://aclanthology.org/2026.finnlp-1.9/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>91</start>
            <end>97</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Trust the Query, Not the Answer: Auditable Text-to-SPARQL over the GLEIF Register
%A Cutura, Jannic Alexander
%Y Huang, Jimin
%Y Lee, Yongjae
%Y Ananiadou, Sophia
%Y Chen, Hsin-Hsi
%Y Takamura, Hiroya
%Y Chen, Chung-Chi
%S Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-466-8
%F cutura-2026-trust
%X Ask which subsidiaries a conglomerate owns, and a language model returns a plausible list, unverifiable and partly wrong; in compliance or supervision, that will not do. So instead of trusting the answer, a local open-weight model translates each question into an auditable SPARQL query over the GLEIF register, returning the query and its source records. A 20B model answers 86.7% of held-out questions correctly, always with a valid query and declining the unanswerable, and no larger open or closed model does better. The method fits any ontology-described source; code and benchmark are released.
%U https://aclanthology.org/2026.finnlp-1.9/
%P 91-97

Download as File

Markdown (Informal)

[Trust the Query, Not the Answer: Auditable Text-to-SPARQL over the GLEIF Register](https://aclanthology.org/2026.finnlp-1.9/) (Cutura, FinNLP 2026)

Trust the Query, Not the Answer: Auditable Text-to-SPARQL over the GLEIF Register (Cutura, FinNLP 2026)

ACL

Jannic Alexander Cutura. 2026. Trust the Query, Not the Answer: Auditable Text-to-SPARQL over the GLEIF Register. In Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing, pages 91–97, Budapest, Hungary. Association for Computational Linguistics.