{"id":"https://openalex.org/W4416034974","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.410","title":"AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmark","display_name":"AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmark","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034974","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.410"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.410","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.410","pdf_url":"https://aclanthology.org/2025.findings-emnlp.410.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: EMNLP 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-emnlp.410.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100373032","display_name":"Lan Li","orcid":"https://orcid.org/0000-0002-9243-8418"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lan Li","raw_affiliation_strings":["School of Information Sciences University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Sciences University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019736712","display_name":"Liri Fang","orcid":"https://orcid.org/0000-0002-0237-3367"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liri Fang","raw_affiliation_strings":["School of Information Sciences University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Sciences University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057600294","display_name":"Bertram Lud\u00e4scher","orcid":"https://orcid.org/0000-0001-9140-936X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bertram Lud\u00e4scher","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079566229","display_name":"Vetle I. Torvik","orcid":"https://orcid.org/0000-0002-0035-1850"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vetle I Torvik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7766","last_page":"7780"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.7957000136375427,"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":0.7957000136375427,"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/T11937","display_name":"Research Data Management Practices","score":0.03959999978542328,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10703","display_name":"Business Process Modeling and Analysis","score":0.0272000003606081,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6065000295639038},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46160000562667847},{"id":"https://openalex.org/keywords/troubleshooting","display_name":"Troubleshooting","score":0.3564999997615814},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.30410000681877136},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.2856000065803528}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6413999795913696},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6065000295639038},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46160000562667847},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3361999988555908},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31369999051094055},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.30550000071525574},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.289900004863739},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2565999925136566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.410","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.410","pdf_url":"https://aclanthology.org/2025.findings-emnlp.410.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.410","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.410","pdf_url":"https://aclanthology.org/2025.findings-emnlp.410.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1912064254","display_name":"Track 4:  Advanced CI Coordination Ecosystem: Monitoring and Measurement Services","funder_award_id":"2137603","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2154383771","display_name":null,"funder_award_id":"2005572","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G2507572247","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G4010157413","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G4676224565","display_name":"ACO: An Open CI Ecosystem to Advance Scientific Discovery (OpenCI)","funder_award_id":"2138296","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4804575867","display_name":"Category I: Crossing the Divide Between Today's Practice and Tomorrow's Science","funder_award_id":"2005572","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G509285653","display_name":"Track 3: COre National Ecosystem for CyberinfrasTructure (CONECT)","funder_award_id":"2138307","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5464919783","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G6664589177","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G6953012893","display_name":null,"funder_award_id":"OAC 2005572","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8300691027","display_name":"Track 2: Customized Multi-tier Assistance, Training, and Computational Help (MATCH) for End User ACCESS to CI","funder_award_id":"2138286","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8897435675","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332222","display_name":"University of Illinois at Urbana-Champaign","ror":"https://ror.org/047426m28"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034974.pdf","grobid_xml":"https://content.openalex.org/works/W4416034974.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Data":[0],"cleaning":[1],"is":[2],"a":[3,29,34,40,48,74,106],"time-consuming":[4],"and":[5,38,68,81,140,158],"errorprone":[6],"manual":[7],"process,":[8],"even":[9],"with":[10,33,76],"modern":[11],"workflow":[12,82,129],"tools":[13],"like":[14],"OpenRefine.Here,":[15],"we":[16,72],"present":[17],"AutoDCWorkflow,":[18,71],"an":[19],"LLM-based":[20],"pipeline":[21,27],"for":[22,84],"automatically":[23],"generating":[24],"data-cleaning":[25],"workflows.The":[26],"takes":[28],"raw":[30],"table":[31,51,104,119],"coupled":[32],"data":[35,60,145],"analysis":[36],"purpose,":[37],"generates":[39,155],"sequence":[41],"of":[42],"OpenRefine":[43],"operations":[44,57],"designed":[45],"to":[46,53,123],"produce":[47,105],"minimal,":[49],"clean":[50],"sufficient":[52],"address":[54,58],"the":[55,102,116,127,131,148],"purpose.Six":[56],"common":[59],"quality":[61,83],"issues,":[62],"including":[63],"format":[64],"inconsistencies,":[65],"type":[66],"errors,":[67],"duplicates.To":[69],"evaluate":[70],"create":[73],"benchmark":[75],"metrics":[77],"assessing":[78],"answers,":[79,159],"data,":[80],"142":[85],"purposes":[86],"using":[87],"96":[88],"tables":[89,157],"across":[90,150],"six":[91],"topics.The":[92],"evaluation":[93],"covers":[94],"three":[95],"key":[96],"dimensions:":[97],"(1)":[98],"Purpose":[99],"Answer:":[100],"can":[101],"cleaned":[103],"correct":[107],"answer?(2)":[108],"Column":[109],"(Value):":[110],"how":[111],"closely":[112],"does":[113,126],"it":[114],"match":[115],"ground":[117,133],"truth":[118],"?(3)":[120],"Workflow":[121],"(Operations):":[122],"what":[124],"extent":[125],"generated":[128],"resemble":[130,168],"humancurated":[132],"truth?Experiments":[134],"show":[135],"that":[136,167],"Llama":[137],"3.1,":[138],"Mistral,":[139],"Gemma":[141,161],"2":[142],"significantly":[143],"enhance":[144],"quality,":[146],"outperforming":[147],"baseline":[149],"all":[151],"metrics.Gemma":[152],"2-27B":[153],"consistently":[154],"high-quality":[156],"while":[160],"2-9B":[162],"excels":[163],"in":[164],"producing":[165],"workflows":[166],"human":[169],"annotations.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}