{"id":"https://openalex.org/W4389519604","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.858","title":"ClusterLLM: Large Language Models as a Guide for Text Clustering","display_name":"ClusterLLM: Large Language Models as a Guide for Text Clustering","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389519604","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.858"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.emnlp-main.858","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.858","pdf_url":"https://aclanthology.org/2023.emnlp-main.858.pdf","source":null,"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 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.emnlp-main.858.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100326579","display_name":"Yuwei Zhang","orcid":"https://orcid.org/0000-0002-4616-1067"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuwei Zhang","raw_affiliation_strings":["University of California, San Diego"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380107","display_name":"Zihan Wang","orcid":"https://orcid.org/0000-0003-0493-2668"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zihan Wang","raw_affiliation_strings":["University of California, San Diego"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039500313","display_name":"Jingbo Shang","orcid":"https://orcid.org/0000-0002-7249-4404"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jingbo Shang","raw_affiliation_strings":["University of California, San Diego"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5039500313"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":6.9131,"has_fulltext":true,"cited_by_count":40,"citation_normalized_percentile":{"value":0.97656317,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"13903","last_page":"13920"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9940999746322632,"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":0.989300012588501,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8758445978164673},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7961136102676392},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.7525855302810669},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6826867461204529},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5301706790924072},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5036413073539734},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4977908134460449},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4291852116584778},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4241585433483124},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33050623536109924},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3294146955013275}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8758445978164673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7961136102676392},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.7525855302810669},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6826867461204529},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5301706790924072},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5036413073539734},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4977908134460449},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4291852116584778},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4241585433483124},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33050623536109924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3294146955013275},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.emnlp-main.858","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.858","pdf_url":"https://aclanthology.org/2023.emnlp-main.858.pdf","source":null,"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 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.emnlp-main.858","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.858","pdf_url":"https://aclanthology.org/2023.emnlp-main.858.pdf","source":null,"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 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[{"id":"https://openalex.org/G2238608405","display_name":null,"funder_award_id":"1U54HG012510-01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4403456761","display_name":null,"funder_award_id":"Bridge2AI","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6412897046","display_name":null,"funder_award_id":"U54HG012510","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8661345283","display_name":null,"funder_award_id":"01251","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332603","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4389519604.pdf"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W1509525679","https://openalex.org/W1585610988","https://openalex.org/W1987971958","https://openalex.org/W1997919544","https://openalex.org/W2101234009","https://openalex.org/W2120303002","https://openalex.org/W2134089414","https://openalex.org/W2139792342","https://openalex.org/W2153839362","https://openalex.org/W2187089797","https://openalex.org/W2251410829","https://openalex.org/W2556467266","https://openalex.org/W2779692282","https://openalex.org/W2950180292","https://openalex.org/W2962852342","https://openalex.org/W2964074409","https://openalex.org/W2969521304","https://openalex.org/W2970641574","https://openalex.org/W2971136144","https://openalex.org/W2998721586","https://openalex.org/W3030583876","https://openalex.org/W3034323190","https://openalex.org/W3045492832","https://openalex.org/W3099910226","https://openalex.org/W3101553402","https://openalex.org/W3106709020","https://openalex.org/W3110446398","https://openalex.org/W3121375627","https://openalex.org/W3123001214","https://openalex.org/W3137513727","https://openalex.org/W3153660069","https://openalex.org/W3156414406","https://openalex.org/W3156636935","https://openalex.org/W3171153522","https://openalex.org/W3177312484","https://openalex.org/W3194782062","https://openalex.org/W3209666692","https://openalex.org/W4210829109","https://openalex.org/W4221167718","https://openalex.org/W4226278401","https://openalex.org/W4245436919","https://openalex.org/W4281719801","https://openalex.org/W4283011496","https://openalex.org/W4285275136","https://openalex.org/W4287120828","https://openalex.org/W4290056061","https://openalex.org/W4292692470","https://openalex.org/W4292779060","https://openalex.org/W4310923309","https://openalex.org/W4311991106","https://openalex.org/W4312278673","https://openalex.org/W4312281441","https://openalex.org/W4312297403","https://openalex.org/W4312637933","https://openalex.org/W4327810158","https://openalex.org/W4361807267","https://openalex.org/W4366343198","https://openalex.org/W4366733439","https://openalex.org/W4382202733","https://openalex.org/W4384662964","https://openalex.org/W4385570594","https://openalex.org/W4385572035","https://openalex.org/W4385572438","https://openalex.org/W4385573933","https://openalex.org/W4385573970","https://openalex.org/W4385734175","https://openalex.org/W4386265460","https://openalex.org/W4386576685","https://openalex.org/W4389519061","https://openalex.org/W4389523802"],"related_works":["https://openalex.org/W1081706099","https://openalex.org/W2370730867","https://openalex.org/W1795405792","https://openalex.org/W2019737068","https://openalex.org/W2899601636","https://openalex.org/W4254379378","https://openalex.org/W3015674157","https://openalex.org/W4206655101","https://openalex.org/W52853789","https://openalex.org/W4237592971"],"abstract_inverted_index":{"We":[0,106],"introduce":[1],"ClusterLLM,":[2],"a":[3,62],"novel":[4],"text":[5],"clustering":[6,57,73,131,173],"framework":[7],"that":[8,25,97,109,154,169],"leverages":[9],"feedback":[10],"from":[11,151],"an":[12,176],"instruction-tuned":[13],"large":[14],"language":[15],"model,":[16],"such":[17],"as":[18],"ChatGPT.":[19,123],"Compared":[20],"with":[21,159],"traditional":[22],"unsupervised":[23],"methods":[24],"builds":[26],"upon":[27],"\"small\"":[28],"embedders,":[29],"ClusterLLM":[30,170],"exhibits":[31],"two":[32],"intriguing":[33],"advantages:":[34],"(1)":[35],"it":[36,51],"enjoys":[37],"the":[38,53,144,149,156,160],"emergent":[39],"capability":[40],"of":[41,179],"LLM":[42],"even":[43],"if":[44],"its":[45],"embeddings":[46],"are":[47,93],"inaccessible;":[48],"and":[49,91,119,140,147],"(2)":[50],"understands":[52],"user's":[54],"preference":[55],"on":[56,72,130,165],"through":[58],"textual":[59],"instruction":[60],"and/or":[61],"few":[63],"annotated":[64],"data.":[65],"First,":[66],"we":[67,125],"prompt":[68,126],"ChatGPT":[69,127,161],"for":[70,115,128],"insights":[71],"perspective":[74],"by":[75,133],"constructing":[76],"hard":[77],"triplet":[78],"questions":[79,137],"<does":[80],"A":[81,139],"better":[82],"correspond":[83],"to":[84,99,103,121,143],"B":[85,90,141],"than":[86],"C>,":[87],"where":[88],"A,":[89],"C":[92],"similar":[94],"data":[95],"points":[96],"belong":[98,142],"different":[100],"clusters":[101],"according":[102],"small":[104,117],"embedder.":[105],"empirically":[107],"show":[108,168],"this":[110],"strategy":[111],"is":[112,155],"both":[113],"effective":[114],"fine-tuning":[116],"embedder":[118],"cost-efficient":[120],"query":[122],"Second,":[124],"helps":[129],"granularity":[132,150],"carefully":[134],"designed":[135],"pairwise":[136],"<do":[138],"same":[145],"category>,":[146],"tune":[148],"cluster":[152],"hierarchies":[153],"most":[157],"consistent":[158],"answers.":[162],"Extensive":[163],"experiments":[164],"14":[166],"datasets":[167],"consistently":[171],"improves":[172],"quality,":[174],"at":[175],"average":[177],"cost":[178],"~$0.6":[180],"per":[181],"dataset.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":11}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}