<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2026-language">
    <titleInfo>
        <title>Can Language Models Learn Typologically Implausible Languages?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tianyang</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tatsuki</namePart>
        <namePart type="family">Kuribayashi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yohei</namePart>
        <namePart type="family">Oseki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ryan</namePart>
        <namePart type="family">Cotterell</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alex</namePart>
        <namePart type="family">Warstadt</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Grammatical features across human languages exhibit intriguing correlations, often attributed to learning biases in humans. Language models (LMs) provide a scalable and naturalistic framework for studying artificial language learning—one not available in human research. We investigate how learnability varies across typologically plausible and implausible languages that closely follow the word order universals identified by linguistic typologists. Our study trains LMs on highly naturalistic counterfactual versions of English (head-initial) and Japanese (head-final). Compared to prior work, our datasets more precisely target the boundary between typological plausibility and implausibility. Our experiments show that LMs learn subtly implausible languages more slowly, though they eventually reach similar performance on some metrics regardless of typological plausibility. These findings suggest that LMs exhibit typologically aligned learning preferences and that certain typological patterns may emerge from general learning biases. https://github.com/sally-xu-42/Typological_Universals.</abstract>
    <identifier type="citekey">xu-etal-2026-language</identifier>
    <identifier type="doi">10.1162/tacl.a.640</identifier>
    <location>
        <url>https://aclanthology.org/2026.tacl-1.27/</url>
    </location>
    <part>
        <date>2026</date>
        <detail type="volume"><number>14</number></detail>
        <extent unit="page">
            <start>588</start>
            <end>611</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Can Language Models Learn Typologically Implausible Languages?
%A Xu, Tianyang
%A Kuribayashi, Tatsuki
%A Oseki, Yohei
%A Cotterell, Ryan
%A Warstadt, Alex
%J Transactions of the Association for Computational Linguistics
%D 2026
%V 14
%I MIT Press
%C Cambridge, MA
%F xu-etal-2026-language
%X Grammatical features across human languages exhibit intriguing correlations, often attributed to learning biases in humans. Language models (LMs) provide a scalable and naturalistic framework for studying artificial language learning—one not available in human research. We investigate how learnability varies across typologically plausible and implausible languages that closely follow the word order universals identified by linguistic typologists. Our study trains LMs on highly naturalistic counterfactual versions of English (head-initial) and Japanese (head-final). Compared to prior work, our datasets more precisely target the boundary between typological plausibility and implausibility. Our experiments show that LMs learn subtly implausible languages more slowly, though they eventually reach similar performance on some metrics regardless of typological plausibility. These findings suggest that LMs exhibit typologically aligned learning preferences and that certain typological patterns may emerge from general learning biases. https://github.com/sally-xu-42/Typological_Universals.
%R 10.1162/tacl.a.640
%U https://aclanthology.org/2026.tacl-1.27/
%U https://doi.org/10.1162/tacl.a.640
%P 588-611

Markdown (Informal)

[Can Language Models Learn Typologically Implausible Languages?](https://aclanthology.org/2026.tacl-1.27/) (Xu et al., TACL 2026)

• Can Language Models Learn Typologically Implausible Languages? (Xu et al., TACL 2026)

ACL

• Tianyang Xu, Tatsuki Kuribayashi, Yohei Oseki, Ryan Cotterell, and Alex Warstadt. 2026. Can Language Models Learn Typologically Implausible Languages?. Transactions of the Association for Computational Linguistics, 14:588–611.