Do Language Models Know Theo Has a Wife? Investigating the Proviso Problem

Tara Azin; Daniel Dumitrescu; Diana Inkpen; Raj Singh

doi:10.63317/547c6dmqaxgx

Do Language Models Know Theo Has a Wife? Investigating the Proviso Problem

Tara Azin, Daniel Dumitrescu, Diana Inkpen, Raj Singh

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

We investigate how language models handle the proviso problem, an unresolved issue in pragmatics where presuppositions in conditional sentences diverge between theoretical and human interpretations. We reformulate this phenomenon as a Natural Language Inference task and introduce a diagnostic dataset designed to probe presupposition projection in conditionals. We evaluate RoBERTa, DeBERTa, LLaMA, and Gemma using explainability analyses. The results show that models broadly align with human judgments but rely on shallow pattern matching rather than semantic or pragmatic reasoning. Our work provides the first computational evaluation framework for the proviso problem and highlights the need for diagnostic, multi-method approaches to assess pragmatic competence and context-dependent meaning in language models.

Anthology ID:: 2026.lrec-1.155
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:: 1977–1988
Language:
External URL:: https://lrec.elra.info/lrec2026-main-155
DOI:: 10.63317/547c6dmqaxgx
Bibkey:
Cite (ACL):: Tara Azin, Daniel Dumitrescu, Diana Inkpen, and Raj Singh. 2026. Do Language Models Know Theo Has a Wife? Investigating the Proviso Problem. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 1977–1988, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):: Do Language Models Know Theo Has a Wife? Investigating the Proviso Problem (Azin et al., LREC 2026)
Copy Citation:

External Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{azin-etal-2026-language,
    title = "Do Language Models Know Theo Has a Wife? Investigating the Proviso Problem",
    author = "Azin, Tara  and
      Dumitrescu, Daniel  and
      Inkpen, Diana  and
      Singh, Raj",
    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-1.155/",
    doi = "10.63317/547c6dmqaxgx",
    pages = "1977--1988",
    abstract = "We investigate how language models handle the proviso problem, an unresolved issue in pragmatics where presuppositions in conditional sentences diverge between theoretical and human interpretations. We reformulate this phenomenon as a Natural Language Inference task and introduce a diagnostic dataset designed to probe presupposition projection in conditionals. We evaluate RoBERTa, DeBERTa, LLaMA, and Gemma using explainability analyses. The results show that models broadly align with human judgments but rely on shallow pattern matching rather than semantic or pragmatic reasoning. Our work provides the first computational evaluation framework for the proviso problem and highlights the need for diagnostic, multi-method approaches to assess pragmatic competence and context-dependent meaning in language models."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="azin-etal-2026-language">
    <titleInfo>
        <title>Do Language Models Know Theo Has a Wife? Investigating the Proviso Problem</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tara</namePart>
        <namePart type="family">Azin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Daniel</namePart>
        <namePart type="family">Dumitrescu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Diana</namePart>
        <namePart type="family">Inkpen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Raj</namePart>
        <namePart type="family">Singh</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>We investigate how language models handle the proviso problem, an unresolved issue in pragmatics where presuppositions in conditional sentences diverge between theoretical and human interpretations. We reformulate this phenomenon as a Natural Language Inference task and introduce a diagnostic dataset designed to probe presupposition projection in conditionals. We evaluate RoBERTa, DeBERTa, LLaMA, and Gemma using explainability analyses. The results show that models broadly align with human judgments but rely on shallow pattern matching rather than semantic or pragmatic reasoning. Our work provides the first computational evaluation framework for the proviso problem and highlights the need for diagnostic, multi-method approaches to assess pragmatic competence and context-dependent meaning in language models.</abstract>
    <identifier type="citekey">azin-etal-2026-language</identifier>
    <identifier type="doi">10.63317/547c6dmqaxgx</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.155/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>1977</start>
            <end>1988</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Do Language Models Know Theo Has a Wife? Investigating the Proviso Problem
%A Azin, Tara
%A Dumitrescu, Daniel
%A Inkpen, Diana
%A Singh, Raj
%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 azin-etal-2026-language
%X We investigate how language models handle the proviso problem, an unresolved issue in pragmatics where presuppositions in conditional sentences diverge between theoretical and human interpretations. We reformulate this phenomenon as a Natural Language Inference task and introduce a diagnostic dataset designed to probe presupposition projection in conditionals. We evaluate RoBERTa, DeBERTa, LLaMA, and Gemma using explainability analyses. The results show that models broadly align with human judgments but rely on shallow pattern matching rather than semantic or pragmatic reasoning. Our work provides the first computational evaluation framework for the proviso problem and highlights the need for diagnostic, multi-method approaches to assess pragmatic competence and context-dependent meaning in language models.
%R 10.63317/547c6dmqaxgx
%U https://aclanthology.org/2026.lrec-1.155/
%U https://doi.org/10.63317/547c6dmqaxgx
%P 1977-1988

Download as File

Markdown (Informal)

[Do Language Models Know Theo Has a Wife? Investigating the Proviso Problem](https://aclanthology.org/2026.lrec-1.155/) (Azin et al., LREC 2026)

Do Language Models Know Theo Has a Wife? Investigating the Proviso Problem (Azin et al., LREC 2026)

ACL

Tara Azin, Daniel Dumitrescu, Diana Inkpen, and Raj Singh. 2026. Do Language Models Know Theo Has a Wife? Investigating the Proviso Problem. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 1977–1988, Palma de Mallorca, Spain. ELRA Language Resource Association.