{"id":"https://openalex.org/W4404181313","doi":"https://doi.org/10.14778/3685800.3685890","title":"RetClean: Retrieval-Based Data Cleaning Using LLMs and Data Lakes","display_name":"RetClean: Retrieval-Based Data Cleaning Using LLMs and Data Lakes","publication_year":2024,"publication_date":"2024-08-01","ids":{"openalex":"https://openalex.org/W4404181313","doi":"https://doi.org/10.14778/3685800.3685890"},"language":"en","primary_location":{"id":"doi:10.14778/3685800.3685890","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3685800.3685890","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085578697","display_name":"Zan Ahmad Naeem","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138380","display_name":"Qatar Cardiovascular Research Center","ror":"https://ror.org/038vyt185","country_code":"QA","type":"healthcare","lineage":["https://openalex.org/I4210138380"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"Zan Ahmad Naeem","raw_affiliation_strings":["QCRI, HBKU, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"QCRI, HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I4210138380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009743322","display_name":"Mohammad Shahmeer Ahmad","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138380","display_name":"Qatar Cardiovascular Research Center","ror":"https://ror.org/038vyt185","country_code":"QA","type":"healthcare","lineage":["https://openalex.org/I4210138380"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Mohammad Shahmeer Ahmad","raw_affiliation_strings":["QCRI, HBKU, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"QCRI, HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I4210138380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074322354","display_name":"Mohamed Y. Eltabakh","orcid":"https://orcid.org/0000-0002-6344-8246"},"institutions":[{"id":"https://openalex.org/I4210138380","display_name":"Qatar Cardiovascular Research Center","ror":"https://ror.org/038vyt185","country_code":"QA","type":"healthcare","lineage":["https://openalex.org/I4210138380"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Mohamed Eltabakh","raw_affiliation_strings":["QCRI, HBKU, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"QCRI, HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I4210138380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026923999","display_name":"Mourad Ouzzani","orcid":"https://orcid.org/0000-0002-4035-3025"},"institutions":[{"id":"https://openalex.org/I4210138380","display_name":"Qatar Cardiovascular Research Center","ror":"https://ror.org/038vyt185","country_code":"QA","type":"healthcare","lineage":["https://openalex.org/I4210138380"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Mourad Ouzzani","raw_affiliation_strings":["QCRI, HBKU, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"QCRI, HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I4210138380"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101824160","display_name":"Nan Tang","orcid":"https://orcid.org/0000-0003-2832-0295"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Nan Tang","raw_affiliation_strings":["HKUST(GZ)/HKUST, China"],"affiliations":[{"raw_affiliation_string":"HKUST(GZ)/HKUST, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5085578697"],"corresponding_institution_ids":["https://openalex.org/I4210138380"],"apc_list":null,"apc_paid":null,"fwci":8.8739,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.98034966,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"17","issue":"12","first_page":"4421","last_page":"4424"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9962999820709229,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9962999820709229,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9642000198364258,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11937","display_name":"Research Data Management Practices","score":0.9495000243186951,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.34267377853393555},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3425915241241455},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34053659439086914},{"id":"https://openalex.org/keywords/environmental-science","display_name":"Environmental science","score":0.33014509081840515}],"concepts":[{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.34267377853393555},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3425915241241455},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34053659439086914},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.33014509081840515}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3685800.3685890","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3685800.3685890","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W3044865082","https://openalex.org/W4321448364"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4,79],"shown":[5],"great":[6],"potential":[7],"in":[8,16,31,36,39,60,170,202],"data":[9,32,41,120,124,130,175],"cleaning,":[10,33],"which":[11],"is":[12,132],"a":[13,40,118,123,127,137,211,230],"fundamental":[14],"task":[15],"all":[17,225],"modern":[18],"applications.":[19],"In":[20,102,190],"this":[21,191],"demo":[22],"proposal,":[23],"we":[24,141,193],"demonstrate":[25],"that":[26,64,77,103,112,233],"indeed":[27],"LLMs":[28,72,178,201,244],"can":[29,58],"assist":[30,59],"e.g.,":[34,51,83,122],"filling":[35],"missing":[37],"values":[38],"table,":[42],"through":[43],"different":[44,243],"approaches.":[45],"For":[46],"example,":[47],"cloud-based":[48],"non-private":[49,62],"LLMs,":[50],"OpenAI":[52],"GPT":[53],"family":[54],"or":[55,87],"Google":[56],"Gemini,":[57],"cleaning":[61,204],"datasets":[63,76],"encompass":[65],"world-knowledge":[66],"information":[67],"(Scenario":[68,166,216],"1).":[69],"However,":[70],"such":[71],"may":[73],"struggle":[74],"with":[75,117,176,242],"they":[78],"never":[80],"encountered":[81],"before,":[82],"local":[84],"enterprise":[85,174],"data,":[86],"when":[88],"the":[89,95,98,114,143,149,163,195,203,235],"user":[90],"requires":[91],"an":[92],"explanation":[93],"of":[94,97,197,214],"source":[96],"suggested":[99],"clean":[100],"values.":[101],"case,":[104],"retrieval-based":[105],"methods":[106],"using":[107],"RAG":[108],"(Retrieval":[109],"Augmented":[110],"Generation)":[111],"complements":[113],"LLM":[115,158],"power":[116,160],"user-provided":[119],"source,":[121],"lake,":[125],"are":[126],"must.":[128],"The":[129],"lake":[131],"indexed,":[133],"and":[134,156,228,240,245],"each":[135],"time":[136],"new":[138],"request":[139],"comes,":[140],"retrieve":[142],"top-":[144],"k":[145],"relevant":[146],"tuples":[147],"to":[148,153,161,238],"user's":[150],"query":[151],"tuple":[152],"be":[154,185],"cleaned":[155],"leverage":[157],"inference":[159],"infer":[162],"correct":[164],"value":[165],"2).":[167],"Nevertheless,":[168],"even":[169],"Scenario":[171],"2,":[172],"sharing":[173],"public":[177],"(an":[179],"externally":[180],"hosted":[181,199],"model)":[182],"might":[183],"not":[184],"feasible":[186],"for":[187],"privacy":[188],"reasons.":[189],"scenario,":[192],"showcase":[194],"practicality":[196],"locally":[198],"small":[200,212],"process,":[205],"especially":[206],"after":[207],"fine-tuning":[208],"them":[209],"on":[210],"number":[213],"examples":[215],"3).":[217],"Our":[218],"proposed":[219],"system,":[220],"RetClean":[221],",":[222],"seamlessly":[223],"supports":[224],"three":[226],"scenarios":[227],"provides":[229],"user-friendly":[231],"GUI":[232],"enables":[234],"VLDB":[236],"audience":[237],"explore":[239],"experiment":[241],"investigate":[246],"their":[247],"trade-offs.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":13}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}