{"id":"https://openalex.org/W4407759282","doi":"https://doi.org/10.1162/tacl.a.640","title":"Can Language Models Learn Typologically Implausible Languages?","display_name":"Can Language Models Learn Typologically Implausible Languages?","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4407759282","doi":"https://doi.org/10.1162/tacl.a.640"},"language":"en","primary_location":{"id":"doi:10.1162/tacl.a.640","doi":"https://doi.org/10.1162/tacl.a.640","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl.a.640","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["ccf-b","cwts-core","doaj","dongbi-b","jufo-1","norway-2","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1162/tacl.a.640","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049469328","display_name":"Tianyang Xu","orcid":"https://orcid.org/0000-0002-9015-3128","observed_orcids":["https://orcid.org/0000-0002-9015-3128"]},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH","US"],"is_corresponding":false,"raw_author_name":"Tianyang Xu","raw_affiliation_strings":["ETH Z\u00fcrich, Switzerland","Toyota Technical Institute at Chicago, USA. sallyxu@ttic.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Toyota Technical Institute at Chicago, USA. sallyxu@ttic.edu","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062574320","display_name":"Tatsuki Kuribayashi","orcid":"https://orcid.org/0000-0001-7762-5576","observed_orcids":["https://orcid.org/0000-0001-7762-5576"]},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Tatsuki Kuribayashi","raw_affiliation_strings":["MBZUAI, UAE. tatsuki.kuribayashi@mbzuai.ac.ae"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MBZUAI, UAE. tatsuki.kuribayashi@mbzuai.ac.ae","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025796706","display_name":"Yohei Oseki","orcid":"https://orcid.org/0000-0002-1189-1588","observed_orcids":["https://orcid.org/0000-0002-1189-1588"]},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yohei Oseki","raw_affiliation_strings":["The University of Tokyo, Japan. oseki@g.ecc.u-tokyo.ac.jp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Japan. oseki@g.ecc.u-tokyo.ac.jp","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061951606","display_name":"Ryan Cotterell","orcid":"https://orcid.org/0000-0003-4080-1833","observed_orcids":["https://orcid.org/0000-0003-4080-1833"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ryan Cotterell","raw_affiliation_strings":["ETH Z\u00fcrich, Switzerland. rcotterell@inf.ethz.ch"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Switzerland. rcotterell@inf.ethz.ch","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089452138","display_name":"Alex Warstadt","orcid":"https://orcid.org/0000-0002-5397-3151","observed_orcids":["https://orcid.org/0000-0002-5397-3151"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]},{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["CH","US"],"is_corresponding":false,"raw_author_name":"Alex Warstadt","raw_affiliation_strings":["ETH Z\u00fcrich, Switzerland","University of California San Diego, USA. awarstadt@ucsd.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"University of California San Diego, USA. awarstadt@ucsd.edu","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00217064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"588","last_page":"611"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.4814000129699707,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.4814000129699707,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.36719998717308044,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10730","display_name":"Language Development and Disorders","score":0.06750000268220901,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/language-models","display_name":"language models","score":0.5519999861717224},{"id":"https://openalex.org/keywords/artificial-language-learning","display_name":"artificial language learning","score":0.7590000033378601},{"id":"https://openalex.org/keywords/head-final-languages","display_name":"head-final languages","score":0.9950000047683716},{"id":"https://openalex.org/keywords/typological-universals","display_name":"typological universals","score":0.5410000085830688},{"id":"https://openalex.org/keywords/learning-bias","display_name":"learning bias","score":0.6729999780654907},{"id":"https://openalex.org/keywords/language-learnability","display_name":"language learnability","score":0.4819999933242798}],"concepts":[{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5274743437767029},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4564528465270996},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3844241201877594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3206046223640442},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.11210688948631287}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1162/tacl.a.640","doi":"https://doi.org/10.1162/tacl.a.640","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl.a.640","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["ccf-b","cwts-core","doaj","dongbi-b","jufo-1","norway-2","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2502.12317","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.12317","pdf_url":"https://arxiv.org/pdf/2502.12317","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.3929/ethz-c-000790306","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/790306","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Working Paper"},{"id":"pmh:doi:10.3929/ethz-c-000799585","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/799585","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"},{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/799585","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/799585","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, 14","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2502.12317","doi":"https://doi.org/10.48550/arxiv.2502.12317","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.12317","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.3929/ethz-c-000799585","doi":"https://doi.org/10.3929/ethz-c-000799585","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-c-000799585","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Other"}],"best_oa_location":{"id":"doi:10.1162/tacl.a.640","doi":"https://doi.org/10.1162/tacl.a.640","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl.a.640","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["ccf-b","cwts-core","doaj","dongbi-b","jufo-1","norway-2","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4412889906","https://openalex.org/W4416344441","https://openalex.org/W4417291044","https://openalex.org/W7166522325","https://openalex.org/W4390897536","https://openalex.org/W7215971204","https://openalex.org/W4415097652","https://openalex.org/W7208706621","https://openalex.org/W4417054893","https://openalex.org/W4416037575"],"abstract_inverted_index":{"Abstract":[0],"Grammatical":[1],"features":[2],"across":[3,40],"human":[4,33],"languages":[5,45,96],"exhibit":[6,117],"intriguing":[7],"correlations,":[8],"often":[9],"attributed":[10],"to":[11,73],"learning":[12,120,131],"biases":[13],"in":[14,32],"humans.":[15],"Language":[16],"models":[17],"(LMs)":[18],"provide":[19],"a":[20],"scalable":[21],"and":[22,43,69,86,122],"naturalistic":[23,63],"framework":[24],"for":[25],"studying":[26],"artificial":[27],"language":[28],"learning\u2014one":[29],"not":[30],"available":[31],"research.":[34],"We":[35],"investigate":[36],"how":[37],"learnability":[38],"varies":[39],"typologically":[41,118],"plausible":[42],"implausible":[44,95],"that":[46,91,115,123],"closely":[47],"follow":[48],"the":[49,81],"word":[50],"order":[51],"universals":[52],"identified":[53],"by":[54],"linguistic":[55],"typologists.":[56],"Our":[57,88],"study":[58],"trains":[59],"LMs":[60,92,116],"on":[61,105],"highly":[62],"counterfactual":[64],"versions":[65],"of":[66,109],"English":[67],"(head-initial)":[68],"Japanese":[70],"(head-final).":[71],"Compared":[72],"prior":[74],"work,":[75],"our":[76],"datasets":[77],"more":[78,97],"precisely":[79],"target":[80],"boundary":[82],"between":[83],"typological":[84,110,125],"plausibility":[85],"implausibility.":[87],"experiments":[89],"show":[90],"learn":[93],"subtly":[94],"slowly,":[98],"though":[99],"they":[100],"eventually":[101],"reach":[102],"similar":[103],"performance":[104],"some":[106],"metrics":[107],"regardless":[108],"plausibility.":[111],"These":[112],"findings":[113],"suggest":[114],"aligned":[119],"preferences":[121],"certain":[124],"patterns":[126],"may":[127],"emerge":[128],"from":[129],"general":[130],"biases.":[132],"https://github.com/sally-xu-42/Typological_Universals.":[133]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2025-02-20T00:00:00"}
