{"id":"https://openalex.org/W4225909425","doi":"https://doi.org/10.48550/arxiv.2203.08913","title":"Memorizing Transformers","display_name":"Memorizing Transformers","publication_year":2022,"publication_date":"2022-03-16","ids":{"openalex":"https://openalex.org/W4225909425","doi":"https://doi.org/10.48550/arxiv.2203.08913"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2203.08913","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.08913","pdf_url":"https://arxiv.org/pdf/2203.08913","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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.08913","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024901763","display_name":"Yuhuai Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wu, Yuhuai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072217103","display_name":"Markus N. Rabe","orcid":"https://orcid.org/0000-0003-4795-7259"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rabe, Markus N.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020043722","display_name":"DeLesley Hutchins","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hutchins, DeLesley","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002183320","display_name":"Christian Szegedy","orcid":"https://orcid.org/0000-0003-4295-1851"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Szegedy, Christian","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024901763"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9825000166893005,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9182000160217285,"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/memorization","display_name":"Memorization","score":0.8928989171981812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8486589193344116},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6204026341438293},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.49454161524772644},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46503135561943054},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.46299678087234497},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45760512351989746},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44964492321014404},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.43015462160110474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4127340316772461},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4018361270427704},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35331621766090393},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1087394654750824},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0799928605556488}],"concepts":[{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.8928989171981812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8486589193344116},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6204026341438293},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.49454161524772644},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46503135561943054},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.46299678087234497},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45760512351989746},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44964492321014404},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.43015462160110474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4127340316772461},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4018361270427704},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35331621766090393},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1087394654750824},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0799928605556488},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2203.08913","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.08913","pdf_url":"https://arxiv.org/pdf/2203.08913","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.2203.08913","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.08913","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.08913","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.08913","pdf_url":"https://arxiv.org/pdf/2203.08913","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"},"sustainable_development_goals":[{"score":0.8799999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093","https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W4287598411","https://openalex.org/W3098382480"],"abstract_inverted_index":{"Language":[0],"models":[1,24,47],"typically":[2],"need":[3],"to":[4,11,51,115],"be":[5],"trained":[6],"or":[7],"finetuned":[8],"in":[9],"order":[10],"acquire":[12],"new":[13,31,38],"knowledge,":[14],"which":[15],"involves":[16],"updating":[17],"their":[18],"weights.":[19],"We":[20,59,100],"instead":[21],"envision":[22],"language":[23,46,76],"that":[25,61,102,126],"can":[26],"simply":[27],"read":[28],"and":[29,81,122,138],"memorize":[30,52],"data":[32],"at":[33],"inference":[34],"time,":[35],"thus":[36],"acquiring":[37],"knowledge":[39],"immediately.":[40],"In":[41],"this":[42],"work,":[43],"we":[44,108,124],"extend":[45],"with":[48],"the":[49,53,103,110,127],"ability":[50],"internal":[54],"representations":[55],"of":[56,70,112,131,134],"past":[57],"inputs.":[58],"demonstrate":[60],"an":[62],"approximate":[63],"kNN":[64],"lookup":[65],"into":[66],"a":[67],"non-differentiable":[68],"memory":[69,113],"recent":[71],"(key,":[72],"value)":[73],"pairs":[74],"improves":[75,106],"modeling":[77],"across":[78],"various":[79],"benchmarks":[80,119],"tasks,":[82],"including":[83,120],"generic":[84],"webtext":[85],"(C4),":[86],"math":[87],"papers":[88],"(arXiv),":[89],"books":[90],"(PG-19),":[91],"code":[92,121],"(Github),":[93],"as":[94,96],"well":[95],"formal":[97],"theorems":[98,139],"(Isabelle).":[99],"show":[101],"performance":[104],"steadily":[105],"when":[107],"increase":[109],"size":[111],"up":[114],"262K":[116],"tokens.":[117],"On":[118],"mathematics,":[123],"find":[125],"model":[128],"is":[129],"capable":[130],"making":[132],"use":[133],"newly":[135],"defined":[136],"functions":[137],"during":[140],"test":[141],"time.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":9}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}