{"id":"https://openalex.org/W4412887914","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1124","title":"Improving Occupational ISCO Classification of Multilingual Swiss Job Postings with LLM-Refined Training Data","display_name":"Improving Occupational ISCO Classification of Multilingual Swiss Job Postings with LLM-Refined Training Data","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887914","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1124"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1124","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1124","pdf_url":"https://aclanthology.org/2025.findings-acl.1124.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1124.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020204173","display_name":"Ann-Sophie Gnehm","orcid":"https://orcid.org/0000-0001-5846-4025"},"institutions":[{"id":"https://openalex.org/I200744771","display_name":"ZHAW Zurich University of Applied Sciences","ror":null,"country_code":"CH","type":null,"lineage":["https://openalex.org/I200744771"]},{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ann-Sophie Gnehm","raw_affiliation_strings":["Department of Sociology University of Zurich Department of Computational Linguistics University of Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Sociology University of Zurich Department of Computational Linguistics University of Zurich","institution_ids":["https://openalex.org/I200744771","https://openalex.org/I202697423"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073027507","display_name":"Simon Clematide","orcid":"https://orcid.org/0000-0003-1365-0662"},"institutions":[{"id":"https://openalex.org/I200744771","display_name":"ZHAW Zurich University of Applied Sciences","ror":null,"country_code":"CH","type":null,"lineage":["https://openalex.org/I200744771"]},{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Simon Clematide","raw_affiliation_strings":["Department of Sociology University of Zurich Department of Computational Linguistics University of Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Sociology University of Zurich Department of Computational Linguistics University of Zurich","institution_ids":["https://openalex.org/I200744771","https://openalex.org/I202697423"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21834","last_page":"21847"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9563999772071838,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9563999772071838,"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/T13629","display_name":"Text Readability and Simplification","score":0.9092000126838684,"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/training","display_name":"Training (meteorology)","score":0.5835927724838257},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5682229995727539},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5366162061691284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31021565198898315},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08014607429504395}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5835927724838257},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5682229995727539},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5366162061691284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31021565198898315},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08014607429504395},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1124","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1124","pdf_url":"https://aclanthology.org/2025.findings-acl.1124.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1124","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1124","pdf_url":"https://aclanthology.org/2025.findings-acl.1124.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G1635897138","display_name":"Swiss Job Markeet Monitor (SJMM","funder_award_id":"229649","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887914.pdf","grobid_xml":"https://content.openalex.org/works/W4412887914.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4230872509"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Classifying":[0],"occupations":[1],"in":[2,46,97,113],"multilingual":[3,110],"job":[4],"postings":[5],"is":[6],"challenging":[7],"due":[8],"to":[9,39,67,72],"noisy":[10],"labels,":[11],"language":[12,35],"variation,":[13],"and":[14,69,85,99],"domain-specific":[15],"terminology.We":[16],"present":[17],"a":[18],"method":[19],"that":[20],"refines":[21],"silverstandard":[22],"ISCO":[23],"labels":[24,43],"by":[25,82],"consolidating":[26],"them":[27],"with":[28,93,119],"predictions":[29],"from":[30,65,90],"pre-fine-tuned":[31],"models,":[32],"using":[33],"large":[34],"model":[36,88],"(LLM)":[37],"evaluations":[38],"resolve":[40],"discrepancies.The":[41],"refined":[42],"are":[44],"used":[45],"Multiple":[47],"Negatives":[48],"Ranking":[49],"(MNR)":[50],"training":[51],"for":[52],"SentenceBERT-based":[53],"classification.This":[54],"approach":[55],"substantially":[56,108],"improves":[57],"performance,":[58],"raising":[59],"Top-1":[60],"accuracy":[61],"on":[62,75],"silver":[63],"data":[64],"37.2%":[66],"58.3%":[68],"reaching":[70],"up":[71],"80%":[73],"precision":[74],"held-out":[76],"data-an":[77],"over":[78],"30-point":[79],"gain":[80],"validated":[81],"both":[83],"GPT":[84],"human":[86],"raters.The":[87],"benefits":[89],"cross-lingual":[91],"transfer,":[92],"particularly":[94],"strong":[95],"gains":[96],"French":[98],"Italian.These":[100],"results":[101],"demonstrate":[102],"hat":[103],"LLMguided":[104],"label":[105],"refinement":[106],"can":[107],"improve":[109],"occupation":[111],"classification":[112],"fine-grained":[114],"taxonomies":[115],"such":[116],"as":[117],"CH-ISCO":[118],"670":[120],"classes.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}