{"id":"https://openalex.org/W4408854165","doi":"https://doi.org/10.1016/j.knosys.2025.113302","title":"LLM4Jobs: Unsupervised occupation extraction and standardization leveraging Large Language Models","display_name":"LLM4Jobs: Unsupervised occupation extraction and standardization leveraging Large Language Models","publication_year":2025,"publication_date":"2025-03-26","ids":{"openalex":"https://openalex.org/W4408854165","doi":"https://doi.org/10.1016/j.knosys.2025.113302"},"language":"en","primary_location":{"id":"doi:10.1016/j.knosys.2025.113302","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2025.113302","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.knosys.2025.113302","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100341097","display_name":"Nan Li","orcid":"https://orcid.org/0000-0002-9963-7794"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Nan Li","raw_affiliation_strings":["IDLAB - Department of Electronics and Information Systems (ELIS), Ghent University, 9000, Ghent, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-9963-7794","affiliations":[{"raw_affiliation_string":"IDLAB - Department of Electronics and Information Systems (ELIS), Ghent University, 9000, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090926391","display_name":"Bo Kang","orcid":"https://orcid.org/0000-0002-9895-9927"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Bo Kang","raw_affiliation_strings":["IDLAB - Department of Electronics and Information Systems (ELIS), Ghent University, 9000, Ghent, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-9895-9927","affiliations":[{"raw_affiliation_string":"IDLAB - Department of Electronics and Information Systems (ELIS), Ghent University, 9000, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076045275","display_name":"Tijl De Bie","orcid":"https://orcid.org/0000-0002-2692-7504"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Tijl De Bie","raw_affiliation_strings":["IDLAB - Department of Electronics and Information Systems (ELIS), Ghent University, 9000, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDLAB - Department of Electronics and Information Systems (ELIS), Ghent University, 9000, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100341097"],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":{"value":3130,"currency":"USD","value_usd":3130},"apc_paid":{"value":3130,"currency":"USD","value_usd":3130},"fwci":4.188,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93384692,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"316","issue":null,"first_page":"113302","last_page":"113302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9966999888420105,"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/T11719","display_name":"Data Quality and Management","score":0.9496999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/standardization","display_name":"Standardization","score":0.8581196069717407},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6208257079124451},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5597671866416931},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.510144054889679},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40221256017684937}],"concepts":[{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.8581196069717407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6208257079124451},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5597671866416931},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.510144054889679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40221256017684937},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/j.knosys.2025.113302","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2025.113302","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},{"id":"pmh:oai:archive.ugent.be:01JS1JW996PTJWV3WTEEKMW1EA","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01JS1JW996PTJWV3WTEEKMW1EA","pdf_url":"https://biblio.ugent.be/publication/01JS1JW996PTJWV3WTEEKMW1EA/file/01JS1JY7QAW54K212XWK9M1NH5.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 1872-7409","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:archive.ugent.be:01HEQ3TR9DB50S4BPR0DKFXTNJ","is_oa":false,"landing_page_url":"http://hdl.handle.net/1854/LU-01HEQ3TR9DB50S4BPR0DKFXTNJ","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/other"}],"best_oa_location":{"id":"doi:10.1016/j.knosys.2025.113302","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2025.113302","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1464064545","display_name":null,"funder_award_id":"3G042220","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G483950878","display_name":"Exploring Data: Theoretical Foundations and Applications to Web, Multimedia, and Omics Data","funder_award_id":"G0F9816N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G5256265187","display_name":"The activation of inactive people: studying thresholds and breakthroughs using AI techniques","funder_award_id":"G073924N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G5938480771","display_name":null,"funder_award_id":"BOF20/IBF/117","funder_id":"https://openalex.org/F4320322603","funder_display_name":"Universiteit Gent"},{"id":"https://openalex.org/G7978628628","display_name":null,"funder_award_id":"101142229","funder_id":"https://openalex.org/F4320316953","funder_display_name":"European Resuscitation Council"},{"id":"https://openalex.org/G7994696512","display_name":null,"funder_award_id":"BOF20/IBF/117","funder_id":"https://openalex.org/F4320335227","funder_display_name":"Bijzonder Onderzoeksfonds UGent"}],"funders":[{"id":"https://openalex.org/F4320316953","display_name":"European Resuscitation Council","ror":"https://ror.org/05s6r7486"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320322603","display_name":"Universiteit Gent","ror":"https://ror.org/00cv9y106"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"},{"id":"https://openalex.org/F4320335227","display_name":"Bijzonder Onderzoeksfonds UGent","ror":"https://ror.org/00cv9y106"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2341199921","https://openalex.org/W2607303097","https://openalex.org/W2756268972","https://openalex.org/W2776485310","https://openalex.org/W2797753066","https://openalex.org/W2889389730","https://openalex.org/W2896457183","https://openalex.org/W2947199057","https://openalex.org/W2949361621","https://openalex.org/W2965373594","https://openalex.org/W3203545879","https://openalex.org/W4205807230","https://openalex.org/W4229060490","https://openalex.org/W4287854593","https://openalex.org/W4309674289","https://openalex.org/W4319057825","https://openalex.org/W4322718191","https://openalex.org/W4380353763","https://openalex.org/W4386576685","https://openalex.org/W4386794805","https://openalex.org/W4389519044","https://openalex.org/W4391335396","https://openalex.org/W4399535075","https://openalex.org/W6767552790","https://openalex.org/W6802135445","https://openalex.org/W6810836094","https://openalex.org/W6839550359"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2378767206","https://openalex.org/W1540871478","https://openalex.org/W328308450","https://openalex.org/W282641168","https://openalex.org/W2376963063","https://openalex.org/W2066396794","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Automated":[0],"occupation":[1,42,121],"extraction":[2,122],"and":[3,9,18,52,63,81,94,123,131,138],"standardization":[4],"from":[5],"free-text":[6],"job":[7,16],"postings":[8],"resumes":[10],"are":[11],"crucial":[12],"for":[13,41,101,116,128],"applications":[14],"like":[15],"recommendation":[17],"labor":[19],"market":[20],"policy":[21],"formation.":[22],"This":[23],"paper":[24],"introduces":[25],"LLM4Jobs,":[26],"a":[27,84,129],"novel":[28],"unsupervised":[29,72],"methodology":[30],"that":[31,68],"taps":[32],"into":[33],"the":[34,48,111,117,126],"capabilities":[35],"of":[36,55,87,113,120],"large":[37],"language":[38,50],"models":[39],"(LLMs)":[40],"coding.":[43],"LLM4Jobs":[44,69],"uniquely":[45],"harnesses":[46],"both":[47,92,136],"natural":[49],"understanding":[51],"generation":[53],"capacities":[54],"LLMs.":[56],"Evaluated":[57],"on":[58,61],"rigorous":[59],"experimentation":[60],"synthetic":[62,93],"real-world":[64,95],"datasets,":[65,96],"we":[66,90],"demonstrate":[67],"consistently":[70],"surpasses":[71],"state-of-the-art":[73],"benchmarks,":[74],"demonstrating":[75],"its":[76],"versatility":[77],"across":[78],"diverse":[79],"datasets":[80],"granularities.":[82],"As":[83],"side":[85],"result":[86],"our":[88],"work,":[89],"present":[91],"which":[97],"may":[98],"be":[99],"instrumental":[100],"subsequent":[102],"research":[103,137],"in":[104],"this":[105,108],"domain.":[106],"Overall,":[107],"investigation":[109],"highlights":[110],"promise":[112],"contemporary":[114],"LLMs":[115],"intricate":[118],"task":[119],"standardization,":[124],"laying":[125],"foundation":[127],"robust":[130],"adaptable":[132],"framework":[133],"relevant":[134],"to":[135],"industrial":[139],"contexts.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-13T07:31:44.756512","created_date":"2025-10-10T00:00:00"}