{"id":"https://openalex.org/W4403051479","doi":"https://doi.org/10.1162/tacl_a_00693","title":"Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrieval","display_name":"Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrieval","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403051479","doi":"https://doi.org/10.1162/tacl_a_00693"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00693","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00693","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00693/2472609/tacl_a_00693.pdf","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,"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"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00693/2472609/tacl_a_00693.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077371707","display_name":"Ohad Rubin","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ohad Rubin","raw_affiliation_strings":["The Blavatnik School of Computer Science, Tel Aviv University, Israel. ohad.rubin@cs.tau.ac.il"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Blavatnik School of Computer Science, Tel Aviv University, Israel. ohad.rubin@cs.tau.ac.il","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045872048","display_name":"Jonathan Berant","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jonathan Berant","raw_affiliation_strings":["The Blavatnik School of Computer Science, Tel Aviv University, Israel. joberant@cs.tau.ac.il"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Blavatnik School of Computer Science, Tel Aviv University, Israel. joberant@cs.tau.ac.il","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":null,"apc_paid":null,"fwci":1.6316,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.85845929,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"12","issue":null,"first_page":"1197","last_page":"1213"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8359148502349854},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7550584077835083},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5811514854431152},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4813476502895355},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44707080721855164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43727171421051025},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.374616414308548},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11297878623008728},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06657063961029053}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8359148502349854},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7550584077835083},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5811514854431152},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4813476502895355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44707080721855164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43727171421051025},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.374616414308548},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11297878623008728},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06657063961029053},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00693","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00693","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00693/2472609/tacl_a_00693.pdf","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,"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:doaj.org/article:a2cceb21dd1a459eb434ef604a7f3942","is_oa":false,"landing_page_url":"https://doaj.org/article/a2cceb21dd1a459eb434ef604a7f3942","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 12 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00693","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00693","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00693/2472609/tacl_a_00693.pdf","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,"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":[{"id":"https://metadata.un.org/sdg/4","score":0.8700000047683716,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403051479.pdf","grobid_xml":"https://content.openalex.org/works/W4403051479.grobid-xml"},"referenced_works_count":68,"referenced_works":["https://openalex.org/W2069870183","https://openalex.org/W2951434086","https://openalex.org/W2963341956","https://openalex.org/W2963347649","https://openalex.org/W2964110616","https://openalex.org/W3015468748","https://openalex.org/W3034561418","https://openalex.org/W3099700870","https://openalex.org/W3118781290","https://openalex.org/W3131922516","https://openalex.org/W3156789018","https://openalex.org/W3157700644","https://openalex.org/W3174401451","https://openalex.org/W3188983256","https://openalex.org/W3200409031","https://openalex.org/W3201233724","https://openalex.org/W4229005866","https://openalex.org/W4252076394","https://openalex.org/W4285225959","https://openalex.org/W4285272557","https://openalex.org/W4287391717","https://openalex.org/W4287855143","https://openalex.org/W4287891464","https://openalex.org/W4301243929","https://openalex.org/W4310633309","https://openalex.org/W4313442864","https://openalex.org/W4320813768","https://openalex.org/W4321593827","https://openalex.org/W4322718191","https://openalex.org/W4353004366","https://openalex.org/W4362655426","https://openalex.org/W4385570085","https://openalex.org/W4385573021","https://openalex.org/W4385573057","https://openalex.org/W4385573102","https://openalex.org/W4388778348","https://openalex.org/W4388979610","https://openalex.org/W4389326242","https://openalex.org/W4389519070","https://openalex.org/W4401042773","https://openalex.org/W6607690188","https://openalex.org/W6621543089","https://openalex.org/W6770251742","https://openalex.org/W6770813465","https://openalex.org/W6771626834","https://openalex.org/W6774222543","https://openalex.org/W6777615688","https://openalex.org/W6778883912","https://openalex.org/W6781533629","https://openalex.org/W6784591795","https://openalex.org/W6786707460","https://openalex.org/W6788175385","https://openalex.org/W6788811087","https://openalex.org/W6795297065","https://openalex.org/W6795887067","https://openalex.org/W6810730852","https://openalex.org/W6811049435","https://openalex.org/W6811340617","https://openalex.org/W6839500301","https://openalex.org/W6845404407","https://openalex.org/W6847643852","https://openalex.org/W6849921291","https://openalex.org/W6850597148","https://openalex.org/W6850625674","https://openalex.org/W6851054131","https://openalex.org/W6851579256","https://openalex.org/W6852731312","https://openalex.org/W6861295083"],"related_works":["https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W3098382480","https://openalex.org/W4287598411","https://openalex.org/W3094871513","https://openalex.org/W3100913109","https://openalex.org/W3198458223","https://openalex.org/W3126642501"],"abstract_inverted_index":{"Abstract":[0],"Retrieval-augmented":[1],"language":[2,164],"models":[3],"(LMs)":[4],"have":[5],"received":[6],"much":[7],"attention":[8],"recently.":[9],"However,":[10],"typically":[11],"the":[12,23,34,37,40,52,73,89,103,120,125,131,139,147,150,184],"retriever":[13,41,132],"is":[14,117,141],"not":[15],"trained":[16],"jointly":[17,62],"as":[18],"a":[19,64,80,86,135,155],"native":[20],"component":[21,133],"of":[22,36,75,108,110,149],"LM,":[24,31],"but":[25],"added":[26],"post-hoc":[27],"to":[28,42,44,72,98,123,142,154,187],"an":[29,56],"already-pretrained":[30],"which":[32,94],"limits":[33],"ability":[35],"LM":[38,66,90,121],"and":[39,58,69,170,173,180],"adapt":[43],"one":[45],"another.":[46],"In":[47],"this":[48],"work,":[49],"we":[50],"propose":[51],"Retrieval-Pretrained":[53],"Transformer":[54],"(RPT),":[55],"architecture":[57],"training":[59,63],"procedure":[60],"for":[61],"retrieval-augmented":[65],"from":[67,114],"scratch":[68],"applying":[70],"it":[71],"task":[74],"modeling":[76,165],"long":[77,87],"texts.":[78],"Given":[79],"recently":[81],"generated":[82],"text":[83],"chunk":[84],"in":[85,102],"document,":[88,104],"computes":[91],"query":[92],"representations,":[93],"are":[95],"then":[96],"used":[97],"retrieve":[99,143],"earlier":[100],"chunks":[101,116,144],"located":[105],"potentially":[106],"tens":[107],"thousands":[109],"tokens":[111],"before.":[112],"Information":[113],"retrieved":[115],"fused":[118],"into":[119],"representations":[122],"predict":[124],"next":[126,151],"target":[127],"chunk.":[128],"We":[129,158],"train":[130],"with":[134],"semantic":[136],"objective,":[137],"where":[138],"goal":[140],"that":[145,175],"increase":[146],"probability":[148],"chunk,":[152],"according":[153],"reference":[156],"LM.":[157],"evaluate":[159],"RPT":[160,176],"on":[161],"four":[162],"long-range":[163],"tasks,":[166],"spanning":[167],"books,":[168],"code,":[169],"mathematical":[171],"writing,":[172],"demonstrate":[174],"improves":[177],"retrieval":[178],"quality":[179],"subsequently":[181],"perplexity":[182],"across":[183],"board":[185],"compared":[186],"strong":[188],"baselines.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}