{"id":"https://openalex.org/W4402590049","doi":"https://doi.org/10.1145/3685650.3685667","title":"TopicTag: Automatic Annotation of NMF Topic Models Using Chain of Thought and Prompt Tuning with LLMs","display_name":"TopicTag: Automatic Annotation of NMF Topic Models Using Chain of Thought and Prompt Tuning with LLMs","publication_year":2024,"publication_date":"2024-08-20","ids":{"openalex":"https://openalex.org/W4402590049","doi":"https://doi.org/10.1145/3685650.3685667"},"language":"en","primary_location":{"id":"doi:10.1145/3685650.3685667","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3685650.3685667","pdf_url":null,"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 ACM Symposium on Document Engineering 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3685650.3685667","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076380072","display_name":"Selma Wanna","orcid":"https://orcid.org/0000-0002-0991-017X"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Selma Wanna","raw_affiliation_strings":["Advanced Research in Cyber Systems, Theoretical Division, Los Alamos National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Research in Cyber Systems, Theoretical Division, Los Alamos National Laboratory, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071250989","display_name":"Nicholas Solovyev","orcid":"https://orcid.org/0009-0003-6995-3862"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas Solovyev","raw_affiliation_strings":["Advanced Research in Cyber Systems, Theoretical Division, Los Alamos National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Research in Cyber Systems, Theoretical Division, Los Alamos National Laboratory, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082439654","display_name":"Ryan Barron","orcid":"https://orcid.org/0009-0005-5045-9527"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Barron","raw_affiliation_strings":["Theoretical Division, Advanced Research in Cyber Systems, Los Alamos National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Theoretical Division, Advanced Research in Cyber Systems, Los Alamos National Laboratory, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066261993","display_name":"Maksim E. Eren","orcid":"https://orcid.org/0000-0002-4362-0256"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maksim E. Eren","raw_affiliation_strings":["Theoretical Division, Advanced Research in Cyber Systems, Los Alamos National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Theoretical Division, Advanced Research in Cyber Systems, Los Alamos National Laboratory, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012614331","display_name":"Manish Bhattarai","orcid":"https://orcid.org/0000-0002-1421-3643"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manish Bhattarai","raw_affiliation_strings":["Theoretical Division, Los Alamos National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Theoretical Division, Los Alamos National Laboratory, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078718511","display_name":"K. \u00d8. Rasmussen","orcid":"https://orcid.org/0000-0002-4029-4723"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kim \u00d8. Rasmussen","raw_affiliation_strings":["Theoretical Division, Los Alamos National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Theoretical Division, Los Alamos National Laboratory, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079029372","display_name":"Boian S. Alexandrov","orcid":"https://orcid.org/0000-0001-8636-4603"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boian S. Alexandrov","raw_affiliation_strings":["Theoretical Division, Los Alamos National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Theoretical Division, Los Alamos National Laboratory, USA","institution_ids":["https://openalex.org/I1343871089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5076380072"],"corresponding_institution_ids":["https://openalex.org/I1343871089"],"apc_list":null,"apc_paid":null,"fwci":2.1026,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.91310744,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9861999750137329,"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/annotation","display_name":"Annotation","score":0.7718439698219299},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6638213396072388},{"id":"https://openalex.org/keywords/chain","display_name":"Chain (unit)","score":0.44297367334365845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4248444437980652},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4131261110305786}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7718439698219299},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6638213396072388},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.44297367334365845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4248444437980652},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4131261110305786},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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:10.1145/3685650.3685667","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3685650.3685667","pdf_url":null,"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 ACM Symposium on Document Engineering 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3685650.3685667","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3685650.3685667","pdf_url":null,"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 ACM Symposium on Document Engineering 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2113855231","https://openalex.org/W2401143219","https://openalex.org/W2509005432","https://openalex.org/W2949676527","https://openalex.org/W3151899381","https://openalex.org/W3193658714","https://openalex.org/W4312802177","https://openalex.org/W4389518669","https://openalex.org/W4389523693","https://openalex.org/W6892398494"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Topic":[0],"modeling":[1],"is":[2,20],"a":[3,21,27,69],"technique":[4],"for":[5,45,71],"organizing":[6],"and":[7,38,48,91,127],"extracting":[8],"themes":[9],"from":[10],"large":[11,97],"collections":[12],"of":[13,89,120],"unstructured":[14],"text.":[15],"Non-negative":[16],"matrix":[17,33],"factorization":[18],"(NMF)":[19],"common":[22],"unsupervised":[23],"approach":[24],"that":[25],"decomposes":[26],"term":[28],"frequency-inverse":[29],"document":[30,128],"frequency":[31],"(TF-IDF)":[32],"to":[34,63,101],"uncover":[35],"latent":[36],"topics":[37],"segment":[39],"the":[40,87,118],"dataset":[41],"accordingly.":[42],"While":[43],"useful":[44],"highlighting":[46],"patterns":[47],"clustering":[49],"documents,":[50],"NMF":[51,79],"does":[52],"not":[53],"provide":[54],"explicit":[55],"topic":[56,73,104],"labels,":[57],"necessitating":[58],"subject":[59],"matter":[60],"experts":[61],"(SMEs)":[62],"assign":[64],"labels":[65],"manually.":[66],"We":[67],"present":[68],"methodology":[70],"automating":[72],"labeling":[74],"in":[75,123],"documents":[76],"clustered":[77],"via":[78],"with":[80],"automatic":[81],"model":[82],"determination":[83],"(NMFk).":[84],"By":[85],"leveraging":[86],"output":[88],"NMFk":[90],"employing":[92],"prompt":[93],"engineering,":[94],"we":[95],"utilize":[96],"language":[98],"models":[99],"(LLMs)":[100],"generate":[102],"accurate":[103],"labels.":[105],"Our":[106],"case":[107],"study":[108],"on":[109,114],"over":[110],"34,000":[111],"scientific":[112],"abstracts":[113],"Knowledge":[115],"Graphs":[116],"demonstrates":[117],"effectiveness":[119],"our":[121],"method":[122],"enhancing":[124],"knowledge":[125],"management":[126],"organization.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
