<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yusoff-etal-2026-large">
    <titleInfo>
        <title>Can Large Language Models Handle Discourse Particles? A Case Study of Colloquial Malay</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mariah</namePart>
        <namePart type="given">Al</namePart>
        <namePart type="given">Giptiah</namePart>
        <namePart type="given">Binte</namePart>
        <namePart type="family">Yusoff</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jakin</namePart>
        <namePart type="family">Tan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bocheng</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Guangliang</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xi</namePart>
        <namePart type="family">Chen</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>Discourse particles, such as “well” and “kind of”, are crucial components that enable LLMs to “speak” more like humans. They are used to convey emotions, intentions, and interpersonal meanings. However, existing studies have not yet built a comprehensive understanding of LLMs’ capabilities in handling discourse particles. Moreover, the limited number of research focuses primarily on high-resource languages such as English, with little attention paid to Southeast Asian languages. In this paper, we (1) propose MalayPrag, a benchmark designed to systematically evaluate and analyse LLMs’ capabilities in handling discourse particles in colloquial Malay; (2) introduce five attributes that provide a linguistically-grounded, unified framework for interpreting pragmatic functions of discourse particles. Applying these two, we prompt ten off-the-shelf LLMs to perform three predication tasks. The experimental results reveal substantial challenges for current LLMs to accurately connect discourse particles and their pragmatic functions in Malay. The provision of the five attributes designed in this study is found to significantly improve the connections, highlighting the need for structured scaffolding for models’ pragmatic competence.</abstract>
    <identifier type="citekey">yusoff-etal-2026-large</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1448/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>33073</start>
            <end>33092</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Can Large Language Models Handle Discourse Particles? A Case Study of Colloquial Malay
%A Yusoff, Mariah Al Giptiah Binte
%A Tan, Jakin
%A Chen, Bocheng
%A Liu, Guangliang
%A Chen, Xi
%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 yusoff-etal-2026-large
%X Discourse particles, such as “well” and “kind of”, are crucial components that enable LLMs to “speak” more like humans. They are used to convey emotions, intentions, and interpersonal meanings. However, existing studies have not yet built a comprehensive understanding of LLMs’ capabilities in handling discourse particles. Moreover, the limited number of research focuses primarily on high-resource languages such as English, with little attention paid to Southeast Asian languages. In this paper, we (1) propose MalayPrag, a benchmark designed to systematically evaluate and analyse LLMs’ capabilities in handling discourse particles in colloquial Malay; (2) introduce five attributes that provide a linguistically-grounded, unified framework for interpreting pragmatic functions of discourse particles. Applying these two, we prompt ten off-the-shelf LLMs to perform three predication tasks. The experimental results reveal substantial challenges for current LLMs to accurately connect discourse particles and their pragmatic functions in Malay. The provision of the five attributes designed in this study is found to significantly improve the connections, highlighting the need for structured scaffolding for models’ pragmatic competence.
%U https://aclanthology.org/2026.emnlp-main.1448/
%P 33073-33092

Markdown (Informal)

[Can Large Language Models Handle Discourse Particles? A Case Study of Colloquial Malay](https://aclanthology.org/2026.emnlp-main.1448/) (Yusoff et al., EMNLP 2026)

• Can Large Language Models Handle Discourse Particles? A Case Study of Colloquial Malay (Yusoff et al., EMNLP 2026)

ACL

• Mariah Al Giptiah Binte Yusoff, Jakin Tan, Bocheng Chen, Guangliang Liu, and Xi Chen. 2026. Can Large Language Models Handle Discourse Particles? A Case Study of Colloquial Malay. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 33073–33092, Budapest, Hungary. Association for Computational Linguistics.