<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="askari-etal-2026-sensitivity">
    <titleInfo>
        <title>Does Sensitivity to Pragmatic Norms Emerge with More Parameters, More Data, or More Conversations?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Raha</namePart>
        <namePart type="family">Askari</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Judith</namePart>
        <namePart type="family">Sieker</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Valerio</namePart>
        <namePart type="family">Basile</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sina</namePart>
        <namePart type="family">Zarrieß</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>While previous work has examined the ability of language models (LMs) to capture pragmatic patterns, it remains understudied to what extent these abilities are shaped by training conditions. To address this gap, we test several models using an existing evaluation paradigm targeting LMs’ sensitivity to conversational norms (Askari et al. 2025). Across three experimental settings, we investigate the role of model size, training dynamics, and data composition in shaping pragmatic competence. Our results show that different pragmatic abilities exhibit distinct learning dynamics across models with varying sizes. While size or data scaling lead to inconsistent gains, exposure to conversational data causes moderate improvements in a modest training setting. Together, our findings suggest that pragmatic competence in LMs is heterogeneous and highlight the importance of targeted training conditions over scale alone for developing pragmatically sensitive models.</abstract>
    <identifier type="citekey">askari-etal-2026-sensitivity</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1718/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>39201</start>
            <end>39216</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Does Sensitivity to Pragmatic Norms Emerge with More Parameters, More Data, or More Conversations?
%A Askari, Raha
%A Sieker, Judith
%A Basile, Valerio
%A Zarrieß, Sina
%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 askari-etal-2026-sensitivity
%X While previous work has examined the ability of language models (LMs) to capture pragmatic patterns, it remains understudied to what extent these abilities are shaped by training conditions. To address this gap, we test several models using an existing evaluation paradigm targeting LMs’ sensitivity to conversational norms (Askari et al. 2025). Across three experimental settings, we investigate the role of model size, training dynamics, and data composition in shaping pragmatic competence. Our results show that different pragmatic abilities exhibit distinct learning dynamics across models with varying sizes. While size or data scaling lead to inconsistent gains, exposure to conversational data causes moderate improvements in a modest training setting. Together, our findings suggest that pragmatic competence in LMs is heterogeneous and highlight the importance of targeted training conditions over scale alone for developing pragmatically sensitive models.
%U https://aclanthology.org/2026.emnlp-main.1718/
%P 39201-39216

Markdown (Informal)

[Does Sensitivity to Pragmatic Norms Emerge with More Parameters, More Data, or More Conversations?](https://aclanthology.org/2026.emnlp-main.1718/) (Askari et al., EMNLP 2026)

• Does Sensitivity to Pragmatic Norms Emerge with More Parameters, More Data, or More Conversations? (Askari et al., EMNLP 2026)

ACL

• Raha Askari, Judith Sieker, Valerio Basile, and Sina Zarrieß. 2026. Does Sensitivity to Pragmatic Norms Emerge with More Parameters, More Data, or More Conversations?. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 39201–39216, Budapest, Hungary. Association for Computational Linguistics.