{"id":"https://openalex.org/W4376123230","doi":"https://doi.org/10.1145/3539618.3591977","title":"SLIM: Sparsified Late Interaction for Multi-Vector Retrieval with Inverted Indexes","display_name":"SLIM: Sparsified Late Interaction for Multi-Vector Retrieval with Inverted Indexes","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4376123230","doi":"https://doi.org/10.1145/3539618.3591977"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3591977","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-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/A5100622897","display_name":"Minghan Li","orcid":"https://orcid.org/0009-0007-8972-7714"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Minghan Li","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032699557","display_name":"Sheng-Chieh Lin","orcid":"https://orcid.org/0000-0002-7989-9703"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sheng-Chieh Lin","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021623012","display_name":"Xueguang Ma","orcid":"https://orcid.org/0000-0003-3430-4910"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xueguang Ma","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jimmy Lin","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100622897"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":1.5555,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85966114,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1954","last_page":"1959"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9958999752998352,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7796919345855713},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6671087145805359},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.555442750453949},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.5510212182998657},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.5017447471618652},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35800161957740784},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.25587332248687744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7796919345855713},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6671087145805359},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.555442750453949},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.5510212182998657},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.5017447471618652},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35800161957740784},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.25587332248687744},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539618.3591977","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2165548363","display_name":null,"funder_award_id":"Canada","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G8284766523","display_name":null,"funder_award_id":"(NSERC)","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2469060249","https://openalex.org/W2560674852","https://openalex.org/W2794557536","https://openalex.org/W2965373594","https://openalex.org/W2983072359","https://openalex.org/W2998702515","https://openalex.org/W3021397474","https://openalex.org/W3090721331","https://openalex.org/W3099700870","https://openalex.org/W3154280800","https://openalex.org/W3154670582","https://openalex.org/W3154755316","https://openalex.org/W3155895380","https://openalex.org/W3156636935","https://openalex.org/W3157758108","https://openalex.org/W3174203100","https://openalex.org/W3175111331","https://openalex.org/W3180230246","https://openalex.org/W3184918446","https://openalex.org/W3188983256","https://openalex.org/W3212725701","https://openalex.org/W3217305727","https://openalex.org/W4206121183","https://openalex.org/W4213009331","https://openalex.org/W4252076394","https://openalex.org/W4281251078","https://openalex.org/W4281486957","https://openalex.org/W4283312953","https://openalex.org/W4285171517","https://openalex.org/W4286969177","https://openalex.org/W4289550880","https://openalex.org/W4306317003","https://openalex.org/W4308163580","https://openalex.org/W4309591926","https://openalex.org/W4320813768","https://openalex.org/W4321162391"],"related_works":["https://openalex.org/W3028990185","https://openalex.org/W2553206896","https://openalex.org/W2368171686","https://openalex.org/W2311422303","https://openalex.org/W3114320778","https://openalex.org/W1579794579","https://openalex.org/W4206418170","https://openalex.org/W1528425630","https://openalex.org/W2114279702","https://openalex.org/W4301952520"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"Sparsified":[3],"Late":[4],"Interaction":[5],"for":[6,162],"Multi-vector":[7,13],"(SLIM)":[8],"retrieval":[9,14,22,97,103],"with":[10,120],"inverted":[11,101],"indexes.":[12],"methods":[15],"have":[16],"demonstrated":[17],"their":[18,62],"effectiveness":[19],"on":[20,34,132,147],"various":[21],"datasets,":[23],"and":[24,53,136,145,167],"among":[25],"them,":[26],"ColBERT":[27,48,140],"is":[28,117],"the":[29,35,112,154,172],"most":[30],"established":[31],"method":[32],"based":[33],"late":[36,84,114],"interaction":[37,85],"of":[38,42,57],"contextualized":[39,73],"token":[40,74,89,160],"embeddings":[41],"pre-trained":[43],"language":[44],"models.":[45],"However,":[46],"efficient":[47,95],"implementations":[49],"require":[50],"complex":[51],"engineering":[52],"cannot":[54],"take":[55],"advantage":[56],"off-the-shelf":[58,121],"search":[59,123],"libraries,":[60],"impeding":[61],"practical":[63],"use.":[64],"To":[65,149],"address":[66],"this":[67],"issue,":[68],"SLIM":[69,128],"first":[70,155],"maps":[71],"each":[72],"vector":[75],"to":[76,110,139,156],"a":[77,106],"sparse,":[78],"high-dimensional":[79],"lexical":[80,122],"space":[81],"before":[82],"performing":[83],"between":[86],"these":[87],"sparse":[88,159],"embeddings.":[90],"We":[91],"then":[92],"introduce":[93],"an":[94],"two-stage":[96],"architecture":[98],"that":[99],"includes":[100],"index":[102],"followed":[104],"by":[105],"score":[107],"refinement":[108],"module":[109],"approximate":[111],"sparsified":[113],"interaction,":[115],"which":[116],"fully":[118],"compatible":[119],"libraries":[124],"such":[125],"as":[126],"Lucene.":[127],"achieves":[129],"competitive":[130],"accuracy":[131],"MS":[133],"MARCO":[134],"Passages":[135],"BEIR":[137],"compared":[138],"while":[141],"being":[142],"much":[143],"smaller":[144],"faster":[146],"CPUs.":[148],"our":[150],"knowledge,":[151],"we":[152],"are":[153,169],"explore":[157],"using":[158],"representations":[161],"multi-vector":[163],"retrieval.":[164],"Source":[165],"code":[166],"data":[168],"integrated":[170],"into":[171],"Pyserini":[173],"IR":[174],"toolkit.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}