{"id":"https://openalex.org/W7108461356","doi":"https://doi.org/10.5281/zenodo.17798468","title":"LanLi2017/LLM4DC: Initial Artifact Release (v1.0.0)","display_name":"LanLi2017/LLM4DC: Initial Artifact Release (v1.0.0)","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7108461356","doi":"https://doi.org/10.5281/zenodo.17798468"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17798468","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17798468","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"},"type":"software","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17798468","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Fang, Liri","orcid":"https://orcid.org/0000-0002-0237-3367"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Liri","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0237-3367","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lud\u00e4scher, Bertram","orcid":"https://orcid.org/0000-0001-9140-936X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lud\u00e4scher, Bertram","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9140-936X","affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Torvik, Vetle","orcid":"https://orcid.org/0000-0002-0035-1850"},"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":"Torvik, Vetle","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":"https://orcid.org/0000-0002-0035-1850","affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8633000254631042},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7398999929428101},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.7264000177383423},{"id":"https://openalex.org/keywords/artifact","display_name":"Artifact (error)","score":0.6850000023841858},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5389000177383423},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.5351999998092651},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.532800018787384},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.3912999927997589},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3896999955177307}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8633000254631042},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7398999929428101},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.7264000177383423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6934000253677368},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.6850000023841858},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.550000011920929},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5389000177383423},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.5351999998092651},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.532800018787384},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.3912999927997589},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3425999879837036},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.32910001277923584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32010000944137573},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3165999948978424},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C60478076","wikidata":"https://www.wikidata.org/wiki/Q3036835","display_name":"Reference data","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17798468","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17798468","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Software"}],"best_oa_location":{"id":"doi:10.5281/zenodo.17798468","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17798468","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Artifact":[0],"for":[1,6,34,98,217,227],"AutoDCWorkflow:":[2,204],"code,":[3],"data,":[4,94],"configs":[5],"LLM":[7],"experiments":[8],"AutoDCWorkflow":[9,191],"Abstract":[10],"Data":[11,206],"cleaning":[12],"is":[13],"a":[14,42,47,53,61,88,121],"time-consuming":[15],"and":[16,51,82,95,157,176,199,210],"error-prone":[17],"manual":[18],"process":[19],"even":[20],"with":[21,46,90],"modern":[22],"workflow":[23,96,145],"tools":[24],"like":[25],"OpenRefine.":[26],"Here,":[27],"we":[28,86],"present":[29],"AutoDCWorkflow,":[30,85],"an":[31],"LLM-based":[32,205],"pipeline":[33,40],"automatically":[35],"generating":[36],"data-cleaning":[37],"workflows.":[38],"The":[39,107],"takes":[41],"raw":[43],"table":[44,64,119],"coupled":[45],"data":[48,74,162],"analysis":[49],"purpose,":[50],"generates":[52,173],"sequence":[54],"of":[55,214],"OpenRefine":[56],"operations":[57,71],"designed":[58],"to":[59,66,139],"produce":[60,120],"minimal,":[62],"clean":[63],"sufficient":[65],"address":[67,72],"the":[68,117,132,143,147,165,215],"purpose.":[69],"Six":[70],"common":[73],"quality":[75,97],"issues":[76],"including":[77],"format":[78],"inconsistencies,":[79],"type":[80],"errors,":[81],"duplicates.To":[83],"evaluate":[84],"create":[87],"benchmark":[89],"metrics":[91],"assessing":[92],"answers,":[93,177],"142":[99],"purposes":[100],"using":[101],"96":[102],"tables":[103,175],"across":[104,167],"six":[105],"topics.":[106],"evaluation":[108],"covers":[109],"three":[110],"key":[111],"dimensions:":[112],"(1)":[113],"Purpose":[114],"Answer:":[115],"can":[116],"cleaned":[118],"correct":[122],"answer?":[123],"(2)":[124],"Column":[125],"(Value):":[126],"how":[127],"closely":[128],"does":[129,142],"it":[130],"match":[131],"ground":[133,149],"truth":[134],"table?":[135],"(3)":[136],"Workflow":[137,208],"(Operations):":[138],"what":[140],"extent":[141],"generated":[144],"resemble":[146,186],"human-curated":[148],"truth?":[150],"Experiments":[151],"show":[152],"that":[153,185],"Llama":[154],"3.1,":[155],"Mistral,":[156],"Gemma":[158,170,179],"2":[159],"significantly":[160],"enhance":[161],"quality,":[163],"outperforming":[164],"baseline":[166],"all":[168],"metrics.":[169],"2-27B":[171],"consistently":[172],"high-quality":[174],"while":[178],"2-9B":[180],"excels":[181],"in":[182],"producing":[183],"workflows":[184],"human":[187],"annotations.":[188],"Please":[189],"cite":[190],"as:":[192],"Lan":[193],"Li,":[194],"Liri":[195],"Fang,":[196],"Bertram":[197],"Lud\u00e4scher,":[198],"Vetle":[200],"I":[201],"Torvik.":[202],"2025.":[203],"Cleaning":[207],"Auto-Generation":[209],"Benchmark.":[211],"In":[212],"Findings":[213],"Association":[216,226],"Computational":[218,228],"Linguistics:":[219],"EMNLP":[220],"2025,":[221],"pages":[222],"7766\u20137780,":[223],"Suzhou,":[224],"China.":[225],"Linguistics.":[229]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-12-04T00:00:00"}