A Discourse-based Tool Series for Logical Validation of LLMs

Boris Galitsky; Dmitry Ilvovsky

doi:10.63317/5fg7umsbz7m5

A Discourse-based Tool Series for Logical Validation of LLMs

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 external publication .)

Authors concatenated from the text boxes above:

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

Abstract

Large Language Models (LLMs) frequently produce fluent but unverifiable reasoning, resulting in potential hallucinations and faulty inferences. This study proposes a logic programming - based verification framework ValidLogic4LLM in which the reasoning expressed by an LLM is transformed into a logic program (LP), probabilistic LP, defeasible LP and abductive LP representing world knowledge and a given problem description—such as a patient health complaint. The LP formed by an LLM is executed within a symbolic reasoning engine, and the resulting inferences are compared to the LLM’s natural-language conclusions. The strength or probability of facts, clauses and arguments is computed based on discourse structure of text expressing these facts or arguments. Divergence between symbolic and neural reasoning outcomes indicates possible hallucination or inconsistency in the model’s internal logic.

Anthology ID:: 2026.lrec-1.174
Volume:: Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:: May
Year:: 2026
Address:: Palma de Mallorca, Spain
Editors:: Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:: LREC
SIG:
Publisher:: ELRA Language Resource Association
Note:
Pages:: 2220–2231
Language:
External URL:: https://lrec.elra.info/lrec2026-main-174
DOI:: 10.63317/5fg7umsbz7m5
Bibkey:
Cite (ACL):: Boris Galitsky and Dmitry Ilvovsky. 2026. A Discourse-based Tool Series for Logical Validation of LLMs. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 2220–2231, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):: A Discourse-based Tool Series for Logical Validation of LLMs (Galitsky & Ilvovsky, LREC 2026)
Copy Citation:

External Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{galitsky-ilvovsky-2026-discourse,
    title = "A Discourse-based Tool Series for Logical Validation of {LLM}s",
    author = "Galitsky, Boris  and
      Ilvovsky, Dmitry",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://aclanthology.org/2026.lrec-1.174/",
    doi = "10.63317/5fg7umsbz7m5",
    pages = "2220--2231",
    abstract = "Large Language Models (LLMs) frequently produce fluent but unverifiable reasoning, resulting in potential hallucinations and faulty inferences. This study proposes a logic programming - based verification framework ValidLogic4LLM in which the reasoning expressed by an LLM is transformed into a logic program (LP), probabilistic LP, defeasible LP and abductive LP representing world knowledge and a given problem description{---}such as a patient health complaint. The LP formed by an LLM is executed within a symbolic reasoning engine, and the resulting inferences are compared to the LLM{'}s natural-language conclusions. The strength or probability of facts, clauses and arguments is computed based on discourse structure of text expressing these facts or arguments. Divergence between symbolic and neural reasoning outcomes indicates possible hallucination or inconsistency in the model{'}s internal logic."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="galitsky-ilvovsky-2026-discourse">
    <titleInfo>
        <title>A Discourse-based Tool Series for Logical Validation of LLMs</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Boris</namePart>
        <namePart type="family">Galitsky</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dmitry</namePart>
        <namePart type="family">Ilvovsky</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 Fifteenth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Núria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henk</namePart>
            <namePart type="family">van den Heuvel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="family">Ide</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Krek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Toral</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resource Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Large Language Models (LLMs) frequently produce fluent but unverifiable reasoning, resulting in potential hallucinations and faulty inferences. This study proposes a logic programming - based verification framework ValidLogic4LLM in which the reasoning expressed by an LLM is transformed into a logic program (LP), probabilistic LP, defeasible LP and abductive LP representing world knowledge and a given problem description—such as a patient health complaint. The LP formed by an LLM is executed within a symbolic reasoning engine, and the resulting inferences are compared to the LLM’s natural-language conclusions. The strength or probability of facts, clauses and arguments is computed based on discourse structure of text expressing these facts or arguments. Divergence between symbolic and neural reasoning outcomes indicates possible hallucination or inconsistency in the model’s internal logic.</abstract>
    <identifier type="citekey">galitsky-ilvovsky-2026-discourse</identifier>
    <identifier type="doi">10.63317/5fg7umsbz7m5</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.174/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>2220</start>
            <end>2231</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T A Discourse-based Tool Series for Logical Validation of LLMs
%A Galitsky, Boris
%A Ilvovsky, Dmitry
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F galitsky-ilvovsky-2026-discourse
%X Large Language Models (LLMs) frequently produce fluent but unverifiable reasoning, resulting in potential hallucinations and faulty inferences. This study proposes a logic programming - based verification framework ValidLogic4LLM in which the reasoning expressed by an LLM is transformed into a logic program (LP), probabilistic LP, defeasible LP and abductive LP representing world knowledge and a given problem description—such as a patient health complaint. The LP formed by an LLM is executed within a symbolic reasoning engine, and the resulting inferences are compared to the LLM’s natural-language conclusions. The strength or probability of facts, clauses and arguments is computed based on discourse structure of text expressing these facts or arguments. Divergence between symbolic and neural reasoning outcomes indicates possible hallucination or inconsistency in the model’s internal logic.
%R 10.63317/5fg7umsbz7m5
%U https://aclanthology.org/2026.lrec-1.174/
%U https://doi.org/10.63317/5fg7umsbz7m5
%P 2220-2231

Download as File

Markdown (Informal)

[A Discourse-based Tool Series for Logical Validation of LLMs](https://aclanthology.org/2026.lrec-1.174/) (Galitsky & Ilvovsky, LREC 2026)

A Discourse-based Tool Series for Logical Validation of LLMs (Galitsky & Ilvovsky, LREC 2026)

ACL

Boris Galitsky and Dmitry Ilvovsky. 2026. A Discourse-based Tool Series for Logical Validation of LLMs. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 2220–2231, Palma de Mallorca, Spain. ELRA Language Resource Association.