{"id":"https://openalex.org/W4412945484","doi":"https://doi.org/10.18653/v1/2025.acl-long.478","title":"Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases","display_name":"Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945484","doi":"https://doi.org/10.18653/v1/2025.acl-long.478"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.478","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.478","pdf_url":"https://aclanthology.org/2025.acl-long.478.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.478.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045250992","display_name":"Michael Y. Hu","orcid":"https://orcid.org/0000-0002-3718-7169"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Y. Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020894677","display_name":"Jackson Petty","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jackson Petty","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705849","display_name":"Chuan Shi","orcid":"https://orcid.org/0000-0002-3734-0266"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuan Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109946254","display_name":"William Merrill","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"William Merrill","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081824828","display_name":"Tal Linzen","orcid":"https://orcid.org/0000-0003-0435-6912"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tal Linzen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.6578,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96107768,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"9691","last_page":"9709"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.7297999858856201,"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":0.7297999858856201,"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/T13156","display_name":"Historical Linguistics and Language Studies","score":0.6287000179290771,"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":0.5963000059127808,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.650467038154602},{"id":"https://openalex.org/keywords/chomsky-hierarchy","display_name":"Chomsky hierarchy","score":0.6139266490936279},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5442550182342529},{"id":"https://openalex.org/keywords/formal-grammar","display_name":"Formal grammar","score":0.41351208090782166},{"id":"https://openalex.org/keywords/formal-language","display_name":"Formal language","score":0.4118425250053406},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.379529744386673},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.36111652851104736},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.19489863514900208},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06541502475738525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.650467038154602},{"id":"https://openalex.org/C92273848","wikidata":"https://www.wikidata.org/wiki/Q190913","display_name":"Chomsky hierarchy","level":3,"score":0.6139266490936279},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5442550182342529},{"id":"https://openalex.org/C171553443","wikidata":"https://www.wikidata.org/wiki/Q373045","display_name":"Formal grammar","level":3,"score":0.41351208090782166},{"id":"https://openalex.org/C146072743","wikidata":"https://www.wikidata.org/wiki/Q192161","display_name":"Formal language","level":2,"score":0.4118425250053406},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.379529744386673},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.36111652851104736},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.19489863514900208},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06541502475738525}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.478","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.478","pdf_url":"https://aclanthology.org/2025.acl-long.478.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.478","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.478","pdf_url":"https://aclanthology.org/2025.acl-long.478.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[{"id":"https://openalex.org/G8645487671","display_name":"CAREER: RI: Structural Linguistic Generalization Through Expert-Designed Tasks","funder_award_id":"2239862","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945484.pdf","grobid_xml":"https://content.openalex.org/works/W4412945484.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1527504055","https://openalex.org/W600362779","https://openalex.org/W4236264548","https://openalex.org/W1501183951","https://openalex.org/W1977800108","https://openalex.org/W2051046595","https://openalex.org/W1540094790","https://openalex.org/W2046912551","https://openalex.org/W2368577169","https://openalex.org/W2149374919"],"abstract_inverted_index":{"Pretraining":[0],"language":[1,5,17,47,75,91,99,119,145],"models":[2,92],"on":[3,27,73,79,97,136,148,193],"formal":[4,16,46,74,84,107,118,178],"can":[6],"improve":[7],"their":[8],"acquisition":[9],"of":[10,14,65,126,140,152,175],"natural":[11,55,77,98,141,153,180],"language.Which":[12],"features":[13],"the":[15,45,50,62,66,114,117,123,127,157,190],"impart":[18],"an":[19],"inductive":[20],"bias":[21],"that":[22,36,83,116],"leads":[23],"to":[24,93,105,179],"effective":[25,37],"transfer?Drawing":[26],"insights":[28],"from":[29,177],"linguistics":[30],"and":[31,57,81,100,160],"complexity":[32],"theory,":[33],"we":[34,170],"hypothesize":[35],"transfer":[38,176],"occurs":[39],"when":[40],"two":[41],"conditions":[42],"are":[43],"met:":[44],"should":[48,59,120],"capture":[49],"dependency":[51],"structures":[52],"present":[53],"in":[54],"language,":[56,154],"it":[58],"remain":[60,187],"within":[61,122],"computational":[63,124],"limitations":[64,125],"model":[67,146],"architecture.We":[68],"experiment":[69],"with":[70,164],"pre-pretraining":[71,129,155,186],"(training":[72],"before":[76],"languages)":[78],"transformers":[80],"find":[82,110],"languages":[85],"capturing":[86],"hierarchical":[87],"dependencies":[88],"indeed":[89],"enable":[90],"achieve":[94],"lower":[95],"loss":[96,131,159],"better":[101,161],"linguistic":[102,162],"generalization":[103,163],"compared":[104],"other":[106],"languages.We":[108],"also":[109,171],"modest":[111],"support":[112],"for":[113,189],"hypothesis":[115],"fall":[121],"architecture.Strikingly,":[128],"reduces":[130],"more":[132],"efficiently":[133],"than":[134],"training":[135],"a":[137,143,165],"matched":[138],"amount":[139],"language.For":[142],"1B-parameter":[144],"trained":[147],"roughly":[149],"1.6B":[150],"tokens":[151],"achieves":[156],"same":[158],"33%":[166],"smaller":[167],"token":[168],"budget.Finally,":[169],"give":[172],"mechanistic":[173],"evidence":[174],"language:":[181],"attention":[182],"heads":[183],"acquired":[184],"during":[185],"crucial":[188],"model's":[191],"performance":[192],"syntactic":[194],"evaluations.":[195],"1":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}