<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mazzaccara-bernardi-2026-emergence">
    <titleInfo>
        <title>The Emergence of the Pragmatic Dimension in Instructed-LMs</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Davide</namePart>
        <namePart type="family">Mazzaccara</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Raffaella</namePart>
        <namePart type="family">Bernardi</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>Instruction-tuning fundamentally transforms how language models process linguistic input and interact with the user. Through the lens of speech act theory, we investigate whether instruction-tuning causes models to shift from prioritizing syntactical form to pragmatic intent. We create a controlled dataset of 400 sentences systematically varying along two dimensions: syntactical structure (declarative vs. interrogative) and communicative intent (assertive vs. request). Using Principal Component Analysis on hidden state representations from Qwen2.5 (1.5B-7B) and models from two other families (Gemma3-1B, and Llama3.2-3B), we reveal a consistent pattern: base models cluster sentences by syntactical form, while instruction-tuned models reorganize representations around pragmatic intent. This syntactic-to-pragmatic shift occurs in middle layers, with declarative requests and interrogative requests—maximally separated in base models—becoming the most similar categories after instruction-tuning. The phenomenon explains how instruction-tuned models correctly interpret indirect speech acts, treating polite declaratives like I’d appreciate corrections” as functionally equivalent to direct interrogatives. Our findings demonstrate that instruction-tuning teaches models to prioritize the communicative dimension over surface form, a fundamental reorganization consistent across model scales and architectures.</abstract>
    <identifier type="citekey">mazzaccara-bernardi-2026-emergence</identifier>
    <identifier type="doi">10.63317/4w4mg24sz9bc</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.390/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>4967</start>
            <end>4973</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T The Emergence of the Pragmatic Dimension in Instructed-LMs
%A Mazzaccara, Davide
%A Bernardi, Raffaella
%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 mazzaccara-bernardi-2026-emergence
%X Instruction-tuning fundamentally transforms how language models process linguistic input and interact with the user. Through the lens of speech act theory, we investigate whether instruction-tuning causes models to shift from prioritizing syntactical form to pragmatic intent. We create a controlled dataset of 400 sentences systematically varying along two dimensions: syntactical structure (declarative vs. interrogative) and communicative intent (assertive vs. request). Using Principal Component Analysis on hidden state representations from Qwen2.5 (1.5B-7B) and models from two other families (Gemma3-1B, and Llama3.2-3B), we reveal a consistent pattern: base models cluster sentences by syntactical form, while instruction-tuned models reorganize representations around pragmatic intent. This syntactic-to-pragmatic shift occurs in middle layers, with declarative requests and interrogative requests—maximally separated in base models—becoming the most similar categories after instruction-tuning. The phenomenon explains how instruction-tuned models correctly interpret indirect speech acts, treating polite declaratives like I’d appreciate corrections” as functionally equivalent to direct interrogatives. Our findings demonstrate that instruction-tuning teaches models to prioritize the communicative dimension over surface form, a fundamental reorganization consistent across model scales and architectures.
%R 10.63317/4w4mg24sz9bc
%U https://aclanthology.org/2026.lrec-1.390/
%U https://doi.org/10.63317/4w4mg24sz9bc
%P 4967-4973

Markdown (Informal)

[The Emergence of the Pragmatic Dimension in Instructed-LMs](https://aclanthology.org/2026.lrec-1.390/) (Mazzaccara & Bernardi, LREC 2026)

• The Emergence of the Pragmatic Dimension in Instructed-LMs (Mazzaccara & Bernardi, LREC 2026)

ACL

• Davide Mazzaccara and Raffaella Bernardi. 2026. The Emergence of the Pragmatic Dimension in Instructed-LMs. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 4967–4973, Palma de Mallorca, Spain. ELRA Language Resource Association.