{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T15:01:46Z","timestamp":1782918106773,"version":"3.54.5"},"reference-count":102,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T00:00:00Z","timestamp":1776988800000},"content-version":"vor","delay-in-days":113,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>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\u2014one 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.<\/jats:p>","DOI":"10.1162\/tacl.a.640","type":"journal-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T16:58:41Z","timestamp":1777049921000},"page":"588-611","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":2,"title":["Can Language Models Learn Typologically Implausible Languages?"],"prefix":"10.1162","volume":"14","author":[{"given":"Tianyang","family":"Xu","sequence":"first","affiliation":[{"name":"ETH Z\u00fcrich, Switzerland"},{"name":"Toyota Technical Institute at Chicago, USA. sallyxu@ttic.edu"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tatsuki","family":"Kuribayashi","sequence":"additional","affiliation":[{"name":"MBZUAI, UAE. tatsuki.kuribayashi@mbzuai.ac.ae"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yohei","family":"Oseki","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Japan. oseki@g.ecc.u-tokyo.ac.jp"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryan","family":"Cotterell","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Switzerland. rcotterell@inf.ethz.ch"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Warstadt","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Switzerland"},{"name":"University of California San Diego, USA. awarstadt@ucsd.edu"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","published-online":{"date-parts":[[2026,4,15]]},"reference":[{"key":"2026042412583540300_bib1","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781107295186","volume-title":"Case: Its Principles and Parameters","author":"Baker","year":"2015"},{"key":"2026042412583540300_bib2","first-page":"351","article-title":"The macroparameter in a microparametric world","volume-title":"The Limits of Syntactic Variation","author":"Baker","year":"2009"},{"key":"2026042412583540300_bib3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1201\/9781003205388-1","article-title":"On the proper role of linguistically-oriented deep net analysis in linguistic theorizing","volume-title":"Algebraic Structures in Natural Language","author":"Baroni","year":"2022"},{"key":"2026042412583540300_bib4","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/978-94-009-2727-8_10","article-title":"Generalized quantifiers and natural language","volume-title":"Philosophy, Language, and Artificial intelligence: Resources for Processing Natural Language","author":"Barwise","year":"1988"},{"key":"2026042412583540300_bib5","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/9780262034241.001.0001","volume-title":"Why Only Us: Language and Evolution","author":"Berwick","year":"2016"},{"key":"2026042412583540300_bib6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/CBO9780511770784.001","article-title":"Introduction: Parameters in minimalist theory","volume-title":"Parametric Variation: Null Subjects in Minimalist Theory","author":"Biberauer","year":"2009"},{"key":"2026042412583540300_bib7","doi-asserted-by":"publisher","first-page":"15115","DOI":"10.18653\/v1\/2024.acl-long.807","article-title":"What languages are easy to language-model? A perspective from learning probabilistic regular languages","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Borenstein","year":"2024"},{"issue":"1","key":"2026042412583540300_bib8","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/S1364-6613(02)00005-0","article-title":"Simplicity: A unifying principle in cognitive science?","volume":"7","author":"Chater","year":"2003","journal-title":"Trends in Cognitive Sciences"},{"issue":"3","key":"2026042412583540300_bib9","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1109\/TIT.1956.1056813","article-title":"Three models for the description of language","volume":"2","author":"Chomsky","year":"1956","journal-title":"IRE Transactions on Information Theory"},{"key":"2026042412583540300_bib10","volume-title":"Aspects of the Theory of Syntax","author":"Chomsky","year":"1965"},{"key":"2026042412583540300_bib11","doi-asserted-by":"publisher","DOI":"10.1515\/9783110884166","volume-title":"Lectures on Government and Binding","author":"Chomsky","year":"1981"},{"key":"2026042412583540300_bib12","doi-asserted-by":"crossref","DOI":"10.1515\/9783110095869.1.9.506","article-title":"The theory of principles and parameters","volume-title":"Syntax: An International Handbook of Contemporary Research","author":"Chomsky","year":"1993"},{"key":"2026042412583540300_bib13","article-title":"Noam Chomsky: The false promise of ChatGPT","author":"Chomsky","year":"2023","journal-title":"The New York Times"},{"issue":"3\u20134","key":"2026042412583540300_bib14","first-page":"309","article-title":"A microparametric approach to the head-initial\/head-final parameter","volume":"41","author":"Cinque","year":"2017","journal-title":"Linguistic Analysis"},{"key":"2026042412583540300_bib15","doi-asserted-by":"crossref","DOI":"10.1002\/9781444390568","volume-title":"Linguistic Nativism and the Poverty of the Stimulus","author":"Clark","year":"2011"},{"key":"2026042412583540300_bib16","doi-asserted-by":"publisher","first-page":"1048","DOI":"10.1162\/tacl_a_00589","article-title":"A cross-linguistic pressure for uniform information density in word order","volume":"11","author":"Clark","year":"2023","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2026042412583540300_bib17","doi-asserted-by":"crossref","unstructured":"Ionut\n              Constantinescu\n            , TiagoPimentel, RyanCotterell, and AlexWarstadt. 2024. Investigating critical period effects in language acquisition through neural language models. 10.1162\/tacl_a_00725","DOI":"10.1162\/tacl_a_00725"},{"key":"2026042412583540300_bib18","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1093\/oso\/9780198747840.003.0002","article-title":"In defence of the child innovator","volume-title":"Micro-change and macro-change in diachronic syntax","author":"Cournane","year":"2017"},{"key":"2026042412583540300_bib19","doi-asserted-by":"publisher","first-page":"104392","DOI":"10.1016\/j.cognition.2020.104392","article-title":"A learning bias for word order harmony: Evidence from speakers of non-harmonic languages","volume":"204","author":"Culbertson","year":"2020","journal-title":"Cognition"},{"key":"2026042412583540300_bib20","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2015.01964","article-title":"Simplicity and specificity in language: Domain-general biases have domain-specific effects","volume":"6","author":"Culbertson","year":"2016","journal-title":"Frontiers in Psychology"},{"key":"2026042412583540300_bib21","article-title":"Syntactic harmony arises from a domain-general learning bias","volume-title":"Proceedings of the 44th Annual Conference of the Cognitive Science Society","author":"Culbertson","year":"2022"},{"key":"2026042412583540300_bib22","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.cognition.2015.02.007","article-title":"Harmonic biases in child learners: In support of language universals","volume":"139","author":"Culbertson","year":"2015","journal-title":"Cognition"},{"issue":"3","key":"2026042412583540300_bib23","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1016\/j.cognition.2011.10.017","article-title":"Learning biases predict a word order universal","volume":"122","author":"Culbertson","year":"2012","journal-title":"Cognition"},{"key":"2026042412583540300_bib24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/coli_a_00402","article-title":"Universal Dependencies","author":"De Marneffe","year":"2021","journal-title":"Computational Linguistics"},{"key":"2026042412583540300_bib25","article-title":"Neural networks and the chomsky hierarchy","volume-title":"Eleventh International Conference on Learning Representations","author":"Del\u00e9tang","year":"2023"},{"key":"2026042412583540300_bib26","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","year":"2021"},{"key":"2026042412583540300_bib27","doi-asserted-by":"crossref","first-page":"138","DOI":"10.2307\/416370","article-title":"The Greenbergian word order correlations","volume":"68","author":"Dryer","year":"1992","journal-title":"Language"},{"key":"2026042412583540300_bib28","article-title":"Learning hierarchical structures with differentiable nondeterministic stacks","volume-title":"International Conference on Learning Representations","author":"DuSell","year":"2022"},{"key":"2026042412583540300_bib29","doi-asserted-by":"publisher","first-page":"4301","DOI":"10.18653\/v1\/2020.findings-emnlp.384","article-title":"How can self-attention networks recognize Dyck-n languages?","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","author":"Ebrahimi","year":"2020"},{"issue":"44","key":"2026042412583540300_bib30","doi-asserted-by":"publisher","first-page":"17897","DOI":"10.1073\/pnas.1215776109","article-title":"Language learners restructure their input to facilitate efficient communication","volume":"109","author":"Fedzechkina","year":"2012","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"2026042412583540300_bib31","first-page":"851","article-title":"Topicalization in language models: A case study on Japanese","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","author":"Fujihara","year":"2022"},{"key":"2026042412583540300_bib32","first-page":"73","article-title":"Some universals of grammar with particular reference to the order of meaningful elements","volume":"2","author":"Greenberg","year":"1963","journal-title":"Universals of language"},{"key":"2026042412583540300_bib33","first-page":"2440","article-title":"Wiki-40B: Multilingual language model dataset","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Guo","year":"2020"},{"issue":"5","key":"2026042412583540300_bib34","doi-asserted-by":"publisher","first-page":"2347","DOI":"10.1073\/pnas.1910923117","article-title":"Universals of word order reflect optimization of grammars for efficient communication","volume":"117","author":"Hahn","year":"2020","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"2026042412583540300_bib35","doi-asserted-by":"publisher","first-page":"17106","DOI":"10.18653\/v1\/2024.emnlp-main.950","article-title":"Do LLMs learn a true syntactic universal?","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","author":"Hale","year":"2024"},{"key":"2026042412583540300_bib36","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1162\/tacl_a_00490","article-title":"Formal language recognition by hard attention transformers: Perspectives from circuit complexity","volume":"10","author":"Hao","year":"2022","journal-title":"Transactions of the Association for Computational Linguistics"},{"issue":"5598","key":"2026042412583540300_bib37","doi-asserted-by":"publisher","first-page":"1569","DOI":"10.1126\/science.298.5598.1569","article-title":"The faculty of language: What is it, who has it, and how did it evolve?","volume":"298","author":"Hauser","year":"2002","journal-title":"Science"},{"key":"2026042412583540300_bib38","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-333370-4.50002-4","volume-title":"Word Order Universals","author":"Hawkins","year":"1983"},{"key":"2026042412583540300_bib39","article-title":"DeBERTa: Decoding enhanced BERT with disentangled attention","volume-title":"International Conference on Learning Representations","author":"He","year":"2021"},{"key":"2026042412583540300_bib40","doi-asserted-by":"publisher","first-page":"85","DOI":"10.18653\/v1\/2022.conll-1.7","article-title":"Towards more natural artificial languages","volume-title":"Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL)","author":"Hopkins","year":"2022"},{"issue":"1","key":"2026042412583540300_bib41","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1111\/tops.12005","article-title":"Language learning from positive evidence, reconsidered: A simplicity-based approach","volume":"5","author":"Hsu","year":"2013","journal-title":"Topics in Cognitive Science"},{"key":"2026042412583540300_bib42","doi-asserted-by":"publisher","first-page":"1725","DOI":"10.18653\/v1\/2020.acl-main.158","article-title":"A systematic assessment of syntactic generalization in neural language models","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Jennifer","year":"2020"},{"key":"2026042412583540300_bib43","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1162\/coli_a_00554","article-title":"Kallini et al. (2024) do not compare impossible languages with constituency-based ones","volume":"51","author":"Hunter","year":"2025","journal-title":"Computational Linguistics"},{"issue":"1\u20132","key":"2026042412583540300_bib44","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1515\/TLIR.2008.003","article-title":"Universals in phonology","volume":"25","author":"Hyman","year":"2008","journal-title":"The Linguistic Review"},{"key":"2026042412583540300_bib45","doi-asserted-by":"publisher","first-page":"4958","DOI":"10.18653\/v1\/2021.findings-acl.439","article-title":"Language models use monotonicity to assess NPI licensing","volume-title":"Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021","author":"Jumelet","year":"2021"},{"key":"2026042412583540300_bib46","doi-asserted-by":"publisher","first-page":"222","DOI":"10.18653\/v1\/W18-5424","article-title":"Do language models understand anything? On the ability of LSTMs to understand negative polarity items","volume-title":"Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","author":"Jumelet","year":"2018"},{"issue":"7873","key":"2026042412583540300_bib47","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"2026042412583540300_bib48","doi-asserted-by":"publisher","first-page":"14691","DOI":"10.18653\/v1\/2024.acl-long.787","article-title":"Mission: Impossible language models","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Kallini","year":"2024"},{"issue":"2","key":"2026042412583540300_bib49","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1080\/15475441.2005.9684215","article-title":"Regularizing unpredictable variation: The roles of adult and child learners in language formation and change","volume":"1","author":"Hudson Kam","year":"2005","journal-title":"Language Learning and Development"},{"issue":"e13153","key":"2026042412583540300_bib50","doi-asserted-by":"publisher","DOI":"10.5964\/bioling.13153","article-title":"Why large language models are poor theories of human linguistic cognition: A reply to Piantadosi","volume":"17","author":"Katzir","year":"2023","journal-title":"Biolinguistics"},{"key":"2026042412583540300_bib51","volume-title":"The Antisymmetry of Syntax","author":"Kayne","year":"1994"},{"issue":"1","key":"2026042412583540300_bib52","article-title":"Why are there no directionality parameters?","volume":"34","author":"Kayne","year":"2013","journal-title":"Studies in Chinese Linguistics"},{"issue":"31","key":"2026042412583540300_bib53","doi-asserted-by":"publisher","first-page":"10681","DOI":"10.1073\/pnas.0707835105","article-title":"Cumulative cultural evolution in the laboratory: An experimental approach to the origins of structure in human language","volume":"105","author":"Kirby","year":"2008","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"2026042412583540300_bib54","article-title":"Why linguistics will thrive in the 21st century: A reply to Piantadosi (2023)","author":"Kodner","year":"2023","journal-title":"arXiv preprint arXiv:2308.03228"},{"key":"2026042412583540300_bib55","article-title":"Mecab: Yet another part-of-speech and morphological analyzer","author":"Kudo","year":"2005"},{"key":"2026042412583540300_bib56","doi-asserted-by":"publisher","first-page":"14522","DOI":"10.18653\/v1\/2024.acl-long.781","article-title":"Emergent word order universals from cognitively-motivated language models","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Kuribayashi","year":"2024"},{"key":"2026042412583540300_bib57","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/ling_a_00533","article-title":"Large language models and the argument from the poverty of the stimulus","author":"Lan","year":"2024","journal-title":"Linguistic Inquiry"},{"issue":"1","key":"2026042412583540300_bib58","doi-asserted-by":"publisher","first-page":"e99\u2013e108","DOI":"10.1353\/lan.2019.0015","article-title":"What can linguistics and deep learning contribute to each other? Response to Pater","volume":"95","author":"Linzen","year":"2019","journal-title":"Language"},{"key":"2026042412583540300_bib59","doi-asserted-by":"publisher","first-page":"1192","DOI":"10.18653\/v1\/D18-1151","article-title":"Targeted syntactic evaluation of language models","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Marvin","year":"2018"},{"issue":"5","key":"2026042412583540300_bib60","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1177\/09637214241268098","article-title":"How can deep neural networks inform theory in psychological science?","volume":"33","author":"McGrath","year":"2024","journal-title":"Current Directions in Psychological Science"},{"key":"2026042412583540300_bib61","article-title":"Language models as models of language","volume-title":"The Oxford Handbook of the Philosophy of Linguistics","author":"Milli\u00e9re","year":"2024"},{"key":"2026042412583540300_bib62","doi-asserted-by":"publisher","first-page":"913","DOI":"10.18653\/v1\/2024.emnlp-main.53","article-title":"Language models learn rare phenomena from less rare phenomena: The case of the missing AANNs","volume-title":"Proceedings of the 2024 conference on empirical methods in natural language processing","author":"Misra","year":"2024"},{"key":"2026042412583540300_bib63","doi-asserted-by":"publisher","first-page":"5147","DOI":"10.18653\/v1\/2020.coling-main.451","article-title":"Priorless recurrent networks learn curiously","volume-title":"Proceedings of the 28th International Conference on Computational Linguistics","author":"Mitchell","year":"2020"},{"key":"2026042412583540300_bib64","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.cortex.2023.07.003","article-title":"Large languages, impossible languages and human brains","volume":"167","author":"Moro","year":"2023","journal-title":"Cortex"},{"key":"2026042412583540300_bib65","article-title":"On the definition of Japanese word","author":"Murawaki","year":"2019"},{"key":"2026042412583540300_bib66","doi-asserted-by":"publisher","first-page":"774","DOI":"10.1038\/nn1077","article-title":"Broca\u2019s area and the language instinct","volume-title":"Nature Neuroscience","author":"Musso","year":"2003"},{"key":"2026042412583540300_bib67","doi-asserted-by":"crossref","DOI":"10.1093\/acprof:oso\/9780199274338.001.0001","volume-title":"Possible and Probable Languages: A Generative Perspective on Linguistic Typology","author":"Newmeyer","year":"2005"},{"key":"2026042412583540300_bib68","first-page":"4034","article-title":"Universal Dependencies v2: An evergrowing multilingual treebank collection","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Nivre","year":"2020"},{"key":"2026042412583540300_bib69","volume-title":"Wa to ga (Wa and ga)","author":"Noda","year":"1996"},{"key":"2026042412583540300_bib70","first-page":"142","article-title":"Word delimitation issues in UD Japanese","volume-title":"Proceedings of the Fifth Workshop on Universal Dependencies (UDW, SyntaxFest 2021)","author":"Omura","year":"2021"},{"issue":"1","key":"2026042412583540300_bib71","doi-asserted-by":"publisher","first-page":"e41","DOI":"10.1353\/lan.2019.0009","article-title":"Generative linguistics and neural networks at 60: Foundation, friction, and fusion","volume":"95","author":"Pater","year":"2019","journal-title":"Language"},{"key":"2026042412583540300_bib72","doi-asserted-by":"publisher","first-page":"1597","DOI":"10.1162\/tacl_a_00720","article-title":"Filtered corpus training (FiCT) shows that language models can generalize from indirect evidence","volume":"12","author":"Patil","year":"2024","journal-title":"Transactions of the Association for Computational Linguistics"},{"issue":"3","key":"2026042412583540300_bib73","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1016\/j.cognition.2010.11.001","article-title":"The learnability of abstract syntactic principles","volume":"118","author":"Perfors","year":"2011","journal-title":"Cognition"},{"key":"2026042412583540300_bib74","article-title":"Transformers generalize linearly","author":"Petty","year":"2021","journal-title":"arXiv:2109.12036 [cs]"},{"issue":"12","key":"2026042412583540300_bib75","doi-asserted-by":"publisher","first-page":"384","DOI":"10.3406\/lgge.2002.2400","article-title":"L\u2019\u00e9volution des formes grammaticales","volume":"6","author":"Peyraube","year":"1912","journal-title":"Scientia; rivista di scienza"},{"key":"2026042412583540300_bib76","first-page":"353","article-title":"Modern language models refute Chomsky\u2019s approach to language","volume-title":"From Fieldwork to Linguistic Theory: A Tribute to Dan Everett","author":"Piantadosi","year":"2023"},{"key":"2026042412583540300_bib77","article-title":"Thoughts on the Universal Dependencies proposal for Japanese: The problem of the word as a linguistic unit","author":"Pringle","year":"2016"},{"key":"2026042412583540300_bib78","doi-asserted-by":"publisher","first-page":"101","DOI":"10.18653\/v1\/2020.acl-demos.14","article-title":"Stanza: A Python natural language processing toolkit for many human languages","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations","author":"Qi","year":"2020"},{"key":"2026042412583540300_bib79","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019"},{"key":"2026042412583540300_bib80","doi-asserted-by":"publisher","first-page":"3532","DOI":"10.18653\/v1\/N19-1356","article-title":"Studying the inductive biases of RNNs with synthetic variations of natural languages","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Ravfogel","year":"2019"},{"issue":"6","key":"2026042412583540300_bib81","doi-asserted-by":"publisher","first-page":"1007","DOI":"10.1207\/s15516709cog0000_28","article-title":"Uncovering the richness of the stimulus: Structure dependence and indirect statistical evidence","volume":"29","author":"Reali","year":"2005","journal-title":"Cognitive Science"},{"key":"2026042412583540300_bib82","doi-asserted-by":"publisher","first-page":"1954","DOI":"10.18653\/v1\/2023.findings-eacl.146","article-title":"Trained on 100 million words and still in shape: BERT meets British National Corpus","volume-title":"Findings of the Association for Computational Linguistics: EACL 2023","author":"Samuel","year":"2023"},{"key":"2026042412583540300_bib83","doi-asserted-by":"publisher","first-page":"1715","DOI":"10.18653\/v1\/P16-1162","article-title":"Neural machine translation of rare words with subword units","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Sennrich","year":"2016"},{"key":"2026042412583540300_bib84","doi-asserted-by":"publisher","first-page":"1581","DOI":"10.18653\/v1\/2023.findings-eacl.117","article-title":"JBLiMP: Japanese benchmark of linguistic minimal pairs","volume-title":"Findings of the Association for Computational Linguistics: EACL 2023","author":"Someya","year":"2023"},{"key":"2026042412583540300_bib85","doi-asserted-by":"publisher","first-page":"27995","DOI":"10.18653\/v1\/2025.acl-long.1357","article-title":"Information locality as an inductive bias for neural language models","volume-title":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Someya","year":"2025"},{"key":"2026042412583540300_bib86","doi-asserted-by":"publisher","first-page":"15595","DOI":"10.63317\/29pwuvvsdqdf","article-title":"Targeted syntactic evaluation on the Chomsky hierarchy","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)","author":"Someya","year":"2024"},{"issue":"3","key":"2026042412583540300_bib87","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1111\/tops.12031","article-title":"Two models of minimalist, incremental syntactic analysis","volume":"5","author":"Stabler","year":"2013","journal-title":"Topics in Cognitive Science"},{"key":"2026042412583540300_bib88","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1162\/tacl_a_00663","article-title":"What formal languages can transformers express? A survey","volume":"12","author":"Strobl","year":"2024","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2026042412583540300_bib89","first-page":"1651","article-title":"Universal Dependencies for Japanese","volume-title":"Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC\u201916)","author":"Tanaka","year":"2016"},{"key":"2026042412583540300_bib90","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1075\/cilt.253.06ter","article-title":"Metafunctional profile of the grammar of Japanese","author":"Teruya","year":"2004","journal-title":"Language typology. A functional Perspective"},{"key":"2026042412583540300_bib91","volume-title":"A Systemic Functional Grammar of Japanese","author":"Teruya","year":"2007"},{"key":"2026042412583540300_bib92","volume-title":"An Introduction to Japanese Linguistics","author":"Tsujimura","year":"2013"},{"key":"2026042412583540300_bib93","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"2026042412583540300_bib94","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1162\/tacl_a_00113","article-title":"The galactic dependencies treebanks: Getting more data by synthesizing new languages","volume":"4","author":"Wang","year":"2016","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2026042412583540300_bib95","doi-asserted-by":"crossref","unstructured":"Alex\n              Warstadt\n            \n          . 2022. Artificial Neural Networks as Models of Human Language Acquisition. PhD Thesis, New York University.","DOI":"10.1201\/9781003205388-2"},{"key":"2026042412583540300_bib96","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1201\/9781003205388-2","article-title":"What artificial neural networks can tell us about human language acquisition","volume-title":"Algebraic Structures in Natural Language","author":"Warstadt","year":"2022"},{"key":"2026042412583540300_bib97","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18653\/v1\/2023.conll-babylm.1","article-title":"Findings of the BabyLM Challenge: Sample-efficient pretraining on developmentally plausible corpora","volume-title":"Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning","author":"Warstadt","year":"2023"},{"key":"2026042412583540300_bib98","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1162\/tacl_a_00321","article-title":"BLiMP: The benchmark of linguistic minimal pairs for English","volume":"8","author":"Warstadt","year":"2020","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2026042412583540300_bib99","doi-asserted-by":"publisher","first-page":"454","DOI":"10.18653\/v1\/2021.acl-long.38","article-title":"Examining the inductive bias of neural language models with artificial languages","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"White","year":"2021"},{"key":"2026042412583540300_bib100","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/ling_a_00491","article-title":"Using computational models to test syntactic learnability","author":"Wilcox","year":"2023","journal-title":"Linguistic Inquiry"},{"issue":"5","key":"2026042412583540300_bib101","doi-asserted-by":"publisher","first-page":"945","DOI":"10.1207\/s15516709cog0000_89","article-title":"Learning phonology with substantive bias: An experimental and computational study of velar palatalization","volume":"30","author":"Wilson","year":"2006","journal-title":"Cognitive Science"},{"key":"2026042412583540300_bib102","doi-asserted-by":"publisher","first-page":"38","DOI":"10.18653\/v1\/2020.emnlp-demos.6","article-title":"Transformers: State-of-the-art natural language processing","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","author":"Wolf","year":"2020"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/TACL.a.640\/2596810\/tacl.a.640.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/TACL.a.640\/2596810\/tacl.a.640.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T16:58:47Z","timestamp":1777049927000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/TACL.a.640\/136431\/Can-Language-Models-Learn-Typologically"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":102,"URL":"https:\/\/doi.org\/10.1162\/tacl.a.640","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026]]},"published":{"date-parts":[[2026]]}}}