<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="foo-etal-2026-stylistic">
    <titleInfo>
        <title>Stylistic Evolution and LLM Neutrality in Singlish Language</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Linus</namePart>
        <namePart type="given">Tze</namePart>
        <namePart type="given">En</namePart>
        <namePart type="family">Foo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Weihan</namePart>
        <namePart type="given">Angela</namePart>
        <namePart type="family">Ng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wenkai</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lynnette</namePart>
        <namePart type="given">Hui</namePart>
        <namePart type="given">Xian</namePart>
        <namePart type="family">Ng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruifeng</namePart>
            <namePart type="family">Xu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ayu</namePart>
            <namePart type="family">Purwarianti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tong</namePart>
            <namePart type="family">Rong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jun</namePart>
            <namePart type="family">Suzuki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hengqin, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-444-6</identifier>
    </relatedItem>
    <abstract>Singlish is a creole rooted in Singapore’s multilingual environment that continues to evolve alongside social and technological change. We examine diachronic stylistic change across a decade of informal digital messages and ask whether Large Language Models (LLMs) can generate temporally neutral outputs approximating the stable characteristics of the variety. Using lexical, pragmatic, psycholinguistic, and encoder-based features, we find that stylistic separability increases with temporal distance, driven primarily by structural features such as length and complexity. Evaluated against a null distribution baseline, most LLMs fail to achieve both authenticity and temporal neutrality simultaneously at their most authentic prompting configuration. This reveals a structural trade-off: models generating realistic Singlish tend to inherit its temporal biases, while temporally neutral models tend to produce inauthentic outputs. These findings position temporal neutrality as a diagnostic metric for assessing sociolectal grounding in LLMs.</abstract>
    <identifier type="citekey">foo-etal-2026-stylistic</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-aacl.41/</url>
    </location>
    <part>
        <date>2026-11</date>
        <extent unit="page">
            <start>778</start>
            <end>790</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Stylistic Evolution and LLM Neutrality in Singlish Language
%A Foo, Linus Tze En
%A Ng, Weihan Angela
%A Li, Wenkai
%A Ng, Lynnette Hui Xian
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F foo-etal-2026-stylistic
%X Singlish is a creole rooted in Singapore’s multilingual environment that continues to evolve alongside social and technological change. We examine diachronic stylistic change across a decade of informal digital messages and ask whether Large Language Models (LLMs) can generate temporally neutral outputs approximating the stable characteristics of the variety. Using lexical, pragmatic, psycholinguistic, and encoder-based features, we find that stylistic separability increases with temporal distance, driven primarily by structural features such as length and complexity. Evaluated against a null distribution baseline, most LLMs fail to achieve both authenticity and temporal neutrality simultaneously at their most authentic prompting configuration. This reveals a structural trade-off: models generating realistic Singlish tend to inherit its temporal biases, while temporally neutral models tend to produce inauthentic outputs. These findings position temporal neutrality as a diagnostic metric for assessing sociolectal grounding in LLMs.
%U https://aclanthology.org/2026.findings-aacl.41/
%P 778-790

Markdown (Informal)

[Stylistic Evolution and LLM Neutrality in Singlish Language](https://aclanthology.org/2026.findings-aacl.41/) (Foo et al., Findings 2026)

• Stylistic Evolution and LLM Neutrality in Singlish Language (Foo et al., Findings 2026)

ACL

• Linus Tze En Foo, Weihan Angela Ng, Wenkai Li, and Lynnette Hui Xian Ng. 2026. Stylistic Evolution and LLM Neutrality in Singlish Language. In Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026, pages 778–790, Hengqin, China. Association for Computational Linguistics.