{"id":"https://openalex.org/W4226462869","doi":"https://doi.org/10.18653/v1/2022.naacl-main.318","title":"Causal Distillation for Language Models","display_name":"Causal Distillation for Language Models","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4226462869","doi":"https://doi.org/10.18653/v1/2022.naacl-main.318"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.naacl-main.318","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.naacl-main.318","pdf_url":"https://aclanthology.org/2022.naacl-main.318.pdf","source":{"id":"https://openalex.org/S4363608774","display_name":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.naacl-main.318.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102822963","display_name":"Zhengxuan Wu","orcid":"https://orcid.org/0000-0001-5581-8908"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhengxuan Wu","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002577142","display_name":"Atticus Geiger","orcid":"https://orcid.org/0000-0002-9170-506X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atticus Geiger","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047850567","display_name":"Josh Rozner","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua Rozner","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073949341","display_name":"Elisa Kreiss","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elisa Kreiss","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065781747","display_name":"Hanson Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanson Lu","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079244248","display_name":"Thomas Icard","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Icard","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042601761","display_name":"Christopher Potts","orcid":"https://orcid.org/0000-0002-7978-6055"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Potts","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001961716","display_name":"Noah D. Goodman","orcid":"https://orcid.org/0000-0002-9176-8802"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Noah Goodman","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5102822963"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02887775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4288","last_page":"4295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9957000017166138,"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/T13629","display_name":"Text Readability and Simplification","score":0.9732000231742859,"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":0.766566276550293},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.7367088794708252},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7242334485054016},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.662717342376709},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5382018089294434},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4984297752380371},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48020753264427185},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.47943466901779175},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4633972942829132},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4200747013092041},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23496094346046448},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07754090428352356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766566276550293},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7367088794708252},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7242334485054016},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.662717342376709},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5382018089294434},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4984297752380371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48020753264427185},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.47943466901779175},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4633972942829132},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4200747013092041},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23496094346046448},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07754090428352356},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2022.naacl-main.318","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.naacl-main.318","pdf_url":"https://aclanthology.org/2022.naacl-main.318.pdf","source":{"id":"https://openalex.org/S4363608774","display_name":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2112.02505","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.02505","pdf_url":"https://arxiv.org/pdf/2112.02505","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2112.02505","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2112.02505","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.25740/kb552zc2656","is_oa":true,"landing_page_url":"https://doi.org/10.25740/kb552zc2656","pdf_url":null,"source":{"id":"https://openalex.org/S7407052831","display_name":"Stanford Digital Repository","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.naacl-main.318","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.naacl-main.318","pdf_url":"https://aclanthology.org/2022.naacl-main.318.pdf","source":{"id":"https://openalex.org/S4363608774","display_name":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8399999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4226462869.pdf","grobid_xml":"https://content.openalex.org/works/W4226462869.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W605621","https://openalex.org/W1226999","https://openalex.org/W193554","https://openalex.org/W12369754","https://openalex.org/W3032909","https://openalex.org/W10287945","https://openalex.org/W17173102","https://openalex.org/W8499301","https://openalex.org/W5952272","https://openalex.org/W745926"],"abstract_inverted_index":{"Distillation":[0],"efforts":[1],"have":[2],"led":[3],"to":[4,21,49,52,68,79,97],"language":[5,34,143,153],"models":[6],"that":[7,40,64,75],"are":[8],"more":[9],"compact":[10],"and":[11,36,121,145,158],"efficient":[12],"without":[13],"serious":[14],"drops":[15],"in":[16,137],"performance.":[17],"The":[18],"standard":[19,129],"approach":[20],"distillation":[22,70,130,133],"trains":[23],"a":[24,30,72,99,107],"student":[25,47,78,95],"model":[26,48,96,105,109],"against":[27],"two":[28],"objectives:":[29],"task-specific":[31],"objective":[32,39,74],"(e.g.,":[33],"modeling)":[35,144],"an":[37],"imitation":[38],"encourages":[41,76],"the":[42,46,55,77,81,86,94,103,111,149],"hidden":[43],"states":[44],"of":[45,54,85,102,131],"be":[50],"similar":[51],"those":[53],"larger":[56],"teacher":[57,87,104],"model.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62],"show":[63],"it":[65],"is":[66,116],"beneficial":[67],"augment":[69],"with":[71,110,124,128],"third":[73],"imitate":[80],"causal":[82,100,113],"computation":[83],"process":[84],"through":[88],"interchange":[89],"intervention":[90],"training(IIT).":[91],"IIT":[92,115,135],"pushes":[93],"become":[98],"abstraction":[101],"-":[106],"simpler":[108],"same":[112],"structure.":[114],"fully":[117],"differentiable,":[118],"easily":[119],"implemented,":[120],"combines":[122],"flexibly":[123],"other":[125],"objectives.":[126],"Compared":[127],"BERT,":[132],"via":[134],"results":[136],"lower":[138],"perplexity":[139],"on":[140,148],"Wikipedia":[141],"(masked":[142],"marked":[146],"improvements":[147],"GLUE":[150],"benchmark":[151],"(natural":[152],"understanding),":[154],"SQuAD":[155],"(question":[156],"answering),":[157],"CoNLL-2003":[159],"(named":[160],"entity":[161],"recognition).":[162]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2022-05-05T00:00:00"}