{"id":"https://openalex.org/W4401863388","doi":"https://doi.org/10.1145/3637528.3671647","title":"TnT-LLM: Text Mining at Scale with Large Language Models","display_name":"TnT-LLM: Text Mining at Scale with Large Language Models","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401863388","doi":"https://doi.org/10.1145/3637528.3671647"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671647","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671647","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671647","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671647","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046172814","display_name":"Mengting Wan","orcid":"https://orcid.org/0000-0002-5298-1221"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mengting Wan","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5298-1221","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019130511","display_name":"Tara Safavi","orcid":"https://orcid.org/0000-0002-3553-4331"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara Safavi","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3553-4331","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036031706","display_name":"Sujay Kumar Jauhar","orcid":"https://orcid.org/0009-0001-9239-6211"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sujay Kumar Jauhar","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0009-0001-9239-6211","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082772530","display_name":"Yujin Kim","orcid":"https://orcid.org/0000-0002-0649-7471"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yujin Kim","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0649-7471","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079717522","display_name":"Scott Counts","orcid":"https://orcid.org/0000-0003-1507-5200"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Counts","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1507-5200","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010290944","display_name":"J. Neville","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jennifer Neville","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0009-0007-1157-018X","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051257652","display_name":"Siddharth Suri","orcid":"https://orcid.org/0000-0002-1318-8140"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Suri","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1318-8140","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061319881","display_name":"Chirag Shah","orcid":"https://orcid.org/0000-0002-3797-4293"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chirag Shah","raw_affiliation_strings":["University of Washington, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3797-4293","affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076259865","display_name":"Ryen W. White","orcid":"https://orcid.org/0000-0002-0265-4249"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryen W. White","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0265-4249","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057330200","display_name":"Longqi Yang","orcid":"https://orcid.org/0000-0002-6615-8615"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Longqi Yang","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6615-8615","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007626895","display_name":"Reid Andersen","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reid Andersen","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0009-0001-4878-6781","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049916734","display_name":"Georg Buscher","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Georg Buscher","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0009-0006-4044-3756","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113246371","display_name":"Dhruv Joshi","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhruv Joshi","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0009-0000-6144-1721","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092949847","display_name":"Nagu Rangan","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nagu Rangan","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0009-0005-3231-2863","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":14,"corresponding_author_ids":["https://openalex.org/A5046172814"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":16.5359,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.99337177,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5836","last_page":"5847"},"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":0.9998000264167786,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.8068154454231262},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5156365633010864},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5138857364654541},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.494304895401001},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44868600368499756},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4085853099822998},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3550906181335449},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34893885254859924},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3303614854812622},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08453208208084106}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8068154454231262},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5156365633010864},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5138857364654541},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.494304895401001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44868600368499756},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4085853099822998},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3550906181335449},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34893885254859924},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3303614854812622},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08453208208084106},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3671647","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671647","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671647","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3637528.3671647","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671647","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671647","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401863388.pdf"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W80463681","https://openalex.org/W1516184288","https://openalex.org/W1987971958","https://openalex.org/W2002011878","https://openalex.org/W2073459066","https://openalex.org/W2104217798","https://openalex.org/W2488678869","https://openalex.org/W2883559670","https://openalex.org/W3023960840","https://openalex.org/W3036644138","https://openalex.org/W3116832844","https://openalex.org/W3134455255","https://openalex.org/W3158986179","https://openalex.org/W3168349005","https://openalex.org/W3173065403","https://openalex.org/W4389519061","https://openalex.org/W4389524280","https://openalex.org/W6668990524","https://openalex.org/W6795224213"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4224009465","https://openalex.org/W4306674287","https://openalex.org/W4286629047","https://openalex.org/W4205958290","https://openalex.org/W4384212932","https://openalex.org/W4390590544","https://openalex.org/W2096195258","https://openalex.org/W2990460313","https://openalex.org/W2973458857"],"abstract_inverted_index":{"Transforming":[0],"unstructured":[1],"text":[2,18],"into":[3],"structured":[4],"and":[5,23,33,44,51,63,87,110,136,166,179,198,208,217,224],"meaningful":[6],"forms,":[7],"organized":[8],"by":[9],"useful":[10],"category":[11],"labels,":[12],"is":[13,54,61],"a":[14,96,126,138,219],"fundamental":[15],"step":[16],"in":[17],"mining":[19],"for":[20,29,116,182,226],"downstream":[21],"analysis":[22,175],"application.":[24],"However,":[25],"most":[26],"existing":[27],"methods":[28],"producing":[30],"label":[31,36,59,108,139,210],"taxonomies":[32,211],"building":[34],"text-based":[35],"classifiers":[37,160],"still":[38],"rely":[39],"heavily":[40],"on":[41],"domain":[42,181],"expertise":[43],"manual":[45],"curation,":[46],"making":[47],"the":[48,58,85,104,121,143,174],"process":[49,105],"expensive":[50],"time-consuming.":[52],"This":[53],"particularly":[55],"challenging":[56],"when":[57,212],"space":[60],"under-specified":[62],"large-scale":[64,90],"data":[65,150],"annotations":[66],"are":[67,147],"unavailable.":[68],"In":[69,120,142],"this":[70],"paper,":[71],"we":[72,124],"address":[73],"these":[74],"challenges":[75],"with":[76,112],"Large":[77],"Language":[78],"Models":[79],"(LLMs),":[80],"whose":[81],"prompt-based":[82],"interface":[83],"facilitates":[84],"induction":[86],"use":[88],"of":[89,106,176],"pseudo":[91],"labels.":[92],"We":[93,170],"propose":[94],"TnT-LLM,":[95],"two-phase":[97],"framework":[98],"that":[99,152,157,203],"employs":[100],"LLMs":[101,133,146],"to":[102,134,173],"automate":[103],"end-to-end":[107],"generation":[109],"assignment":[111],"minimal":[113],"human":[114,197],"effort":[115],"any":[117],"given":[118],"use-case.":[119],"first":[122],"phase,":[123,145],"introduce":[125],"zero-shot,":[127],"multi-stage":[128],"reasoning":[129],"approach":[130],"which":[131],"enables":[132],"produce":[135],"refine":[137],"taxonomy":[140],"iteratively.":[141],"second":[144],"used":[148],"as":[149],"labelers":[151],"yield":[153],"training":[154],"samples":[155],"so":[156],"lightweight":[158],"supervised":[159],"can":[161],"be":[162],"reliably":[163],"built,":[164],"deployed,":[165],"served":[167],"at":[168,228],"scale.":[169,229],"apply":[171],"TnT-LLM":[172,204],"user":[177],"intent":[178],"conversational":[180],"Bing":[183,186],"Copilot":[184],"(formerly":[185],"Chat),":[187],"an":[188],"open-domain":[189],"chat-based":[190],"search":[191],"engine.":[192],"Extensive":[193],"experiments":[194],"using":[195],"both":[196],"automatic":[199],"evaluation":[200],"metrics":[201],"demonstrate":[202],"generates":[205],"more":[206],"accurate":[207],"relevant":[209],"compared":[213],"against":[214],"state-of-the-art":[215],"baselines,":[216],"achieves":[218],"favorable":[220],"balance":[221],"between":[222],"accuracy":[223],"efficiency":[225],"classification":[227]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":34},{"year":2024,"cited_by_count":8}],"updated_date":"2026-05-29T09:21:14.243279","created_date":"2025-10-10T00:00:00"}