{"id":"https://openalex.org/W4416415664","doi":"https://doi.org/10.1145/3777550","title":"Learning Discrete Identifiers and Dense Vectors for Generative Retrieval","display_name":"Learning Discrete Identifiers and Dense Vectors for Generative Retrieval","publication_year":2025,"publication_date":"2025-11-20","ids":{"openalex":"https://openalex.org/W4416415664","doi":"https://doi.org/10.1145/3777550"},"language":"en","primary_location":{"id":"doi:10.1145/3777550","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3777550","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018734145","display_name":"Yunfan Xie","orcid":"https://orcid.org/0009-0003-0854-2525"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfan Xie","raw_affiliation_strings":["Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan,\u00a0China","Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, China"],"raw_orcid":"https://orcid.org/0009-0003-0854-2525","affiliations":[{"raw_affiliation_string":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan,\u00a0China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089307887","display_name":"Lixin Zou","orcid":"https://orcid.org/0000-0001-6755-871X"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lixin Zou","raw_affiliation_strings":["Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan,\u00a0China","Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, China"],"raw_orcid":"https://orcid.org/0000-0001-6755-871X","affiliations":[{"raw_affiliation_string":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan,\u00a0China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102018721","display_name":"Xiangyang Luo","orcid":"https://orcid.org/0000-0001-6062-2950"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyang Luo","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, Henan, China","Institute of Information Engineering, Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0001-6062-2950","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, Henan, China","institution_ids":[]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062665223","display_name":"Hengyi Cai","orcid":"https://orcid.org/0000-0002-7147-5666"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengyi Cai","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","Institute of Information Engineering, Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0002-7147-5666","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chaoran Zhang","orcid":"https://orcid.org/0009-0003-2475-9038"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoran Zhang","raw_affiliation_strings":["Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China","Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, China"],"raw_orcid":"https://orcid.org/0009-0003-2475-9038","affiliations":[{"raw_affiliation_string":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liming Dong","orcid":"https://orcid.org/0000-0002-8676-0363"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liming Dong","raw_affiliation_strings":["National Defense University, Beijing, China","National Defense University, China"],"raw_orcid":"https://orcid.org/0000-0002-8676-0363","affiliations":[{"raw_affiliation_string":"National Defense University, Beijing, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Defense University, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101641900","display_name":"Xixun Lin","orcid":"https://orcid.org/0009-0004-6645-0597"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xixun Lin","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","Institute of Information Engineering, Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0009-0004-6645-0597","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chenliang Li","orcid":"https://orcid.org/0000-0003-3144-6374"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenliang Li","raw_affiliation_strings":["Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China","Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, China"],"raw_orcid":"https://orcid.org/0000-0003-3144-6374","affiliations":[{"raw_affiliation_string":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"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":0.44893073,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"44","issue":"2","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.7809000015258789,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.7809000015258789,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10028","display_name":"Topic Modeling","score":0.04529999941587448,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.02449999935925007,"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/identifier","display_name":"Identifier","score":0.8374999761581421},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6360999941825867},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5634999871253967},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.5516999959945679},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.5212000012397766},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.48739999532699585},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.44020000100135803},{"id":"https://openalex.org/keywords/divergence-from-randomness-model","display_name":"Divergence-from-randomness model","score":0.39969998598098755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8787999749183655},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.8374999761581421},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6639999747276306},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6360999941825867},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5634999871253967},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.5516999959945679},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.5212000012397766},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.48739999532699585},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.44020000100135803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.420199990272522},{"id":"https://openalex.org/C149189445","wikidata":"https://www.wikidata.org/wiki/Q5283894","display_name":"Divergence-from-randomness model","level":3,"score":0.39969998598098755},{"id":"https://openalex.org/C116425068","wikidata":"https://www.wikidata.org/wiki/Q4686695","display_name":"Adversarial information retrieval","level":5,"score":0.39320001006126404},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C22639730","wikidata":"https://www.wikidata.org/wiki/Q7702546","display_name":"Term Discrimination","level":5,"score":0.3479999899864197},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3111000061035156},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.3089999854564667},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.302700012922287},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2985000014305115},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C2985933255","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Text retrieval","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3777550","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3777550","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G371017935","display_name":null,"funder_award_id":"U23A20305 and 62302345","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8503653758","display_name":null,"funder_award_id":"254000510007","funder_id":"https://openalex.org/F4320327776","funder_display_name":"Innovation Scientists and Technicians Troop Construction Projects of Henan Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327776","display_name":"Innovation Scientists and Technicians Troop Construction Projects of Henan Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2136189984","https://openalex.org/W2421218773","https://openalex.org/W2998702515","https://openalex.org/W3023238803","https://openalex.org/W3134665270","https://openalex.org/W3154280800","https://openalex.org/W3154670582","https://openalex.org/W3155895380","https://openalex.org/W4212907295","https://openalex.org/W4385572521","https://openalex.org/W4386302269","https://openalex.org/W4389520393","https://openalex.org/W4389520758","https://openalex.org/W4393096553","https://openalex.org/W4396723267","https://openalex.org/W4400530959","https://openalex.org/W4403369796","https://openalex.org/W6967720068"],"related_works":[],"abstract_inverted_index":{"Generative":[0],"retrieval":[1,13,31,48,77,107,110,132],"presents":[2],"a":[3,23,44,62,126,139,149,158,164],"promising":[4],"approach":[5],"to":[6,26,43,75,101],"information":[7],"retrieval,":[8],"streamlining":[9],"both":[10,193],"indexing":[11],"and":[12,79,108,153,172,189,195],"processes":[14],"through":[15],"end-to-end":[16,136,166],"optimization.":[17],"This":[18],"method":[19,180],"typically":[20],"involves":[21],"assigning":[22],"unique":[24],"identifier":[25,40,60],"each":[27],"document,":[28],"with":[29],"the":[30,34,37,103,118,121,131,141,144,178,182],"goal":[32],"being":[33],"generation":[35],"of":[36,81,105,187],"correct":[38],"document":[39,59,90],"in":[41,53,83,134,157,185],"response":[42],"query.":[45],"Although":[46],"generative":[47,106],"has":[49],"demonstrated":[50],"empirical":[51],"success":[52],"various":[54],"tasks,":[55],"designing":[56],"an":[57,112,135],"effective":[58],"remains":[61],"challenge.":[63],"Previous":[64],"studies":[65],"have":[66,86],"either":[67],"depended":[68],"excessively":[69],"on":[70],"one-to-one":[71],"discrete":[72,122],"identifiers,":[73,91],"leading":[74],"increased":[76],"latency":[78],"loss":[80],"semantics":[82],"documents":[84,156],"or":[85],"used":[87],"retrieval-agnostic":[88],"dense":[89,109,145],"which":[92],"can":[93],"hinder":[94],"performance.":[95],"To":[96],"this":[97],"end,":[98],"we":[99,162],"propose":[100],"integrate":[102],"benefits":[104],"using":[111],"encoder-decoder-based":[113],"pre-trained":[114],"language":[115],"model.":[116],"Particularly,":[117],"decoder,":[119],"i.e.,":[120,143],"identifier,":[123],"functions":[124],"as":[125,148],"coarse":[127],"retriever,":[128,151],"effectively":[129],"reducing":[130],"space":[133],"manner.":[137],"As":[138],"complement,":[140],"encoder,":[142],"vector,":[146],"serves":[147],"fine-grained":[150],"efficiently":[152],"precisely":[154],"ranking":[155],"condensed":[159],"space.":[160],"Accordingly,":[161],"introduce":[163],"three-stage":[165],"learning":[167],"framework":[168],"that":[169,177],"optimizes":[170],"identifiers":[171],"vectors.":[173],"Extensive":[174],"experiments":[175],"reveal":[176],"proposed":[179],"exceeds":[181],"current":[183],"models":[184],"terms":[186],"effectiveness":[188],"time":[190],"efficiency,":[191],"across":[192],"small":[194],"larger":[196],"corpus":[197],"sets.":[198]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-20T00:00:00"}