{"id":"https://openalex.org/W4403536613","doi":"https://doi.org/10.1145/3691620.3695267","title":"AutoDW: Automatic Data Wrangling Leveraging Large Language Models","display_name":"AutoDW: Automatic Data Wrangling Leveraging Large Language Models","publication_year":2024,"publication_date":"2024-10-18","ids":{"openalex":"https://openalex.org/W4403536613","doi":"https://doi.org/10.1145/3691620.3695267"},"language":"en","primary_location":{"id":"doi:10.1145/3691620.3695267","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3691620.3695267","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3691620.3695267","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043386419","display_name":"Lei Liu","orcid":"https://orcid.org/0000-0003-2850-2048"},"institutions":[{"id":"https://openalex.org/I4210094759","display_name":"Fujitsu (United States)","ror":"https://ror.org/0073whr05","country_code":"US","type":"company","lineage":["https://openalex.org/I2252096349","https://openalex.org/I4210094759"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Liu","raw_affiliation_strings":["Fujitsu Research of America Inc., Santa Clara, California, USA"],"raw_orcid":"https://orcid.org/0000-0003-2850-2048","affiliations":[{"raw_affiliation_string":"Fujitsu Research of America Inc., Santa Clara, California, USA","institution_ids":["https://openalex.org/I4210094759"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075190149","display_name":"So Hasegawa","orcid":"https://orcid.org/0009-0003-2239-1014"},"institutions":[{"id":"https://openalex.org/I4210094759","display_name":"Fujitsu (United States)","ror":"https://ror.org/0073whr05","country_code":"US","type":"company","lineage":["https://openalex.org/I2252096349","https://openalex.org/I4210094759"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"So Hasegawa","raw_affiliation_strings":["Fujitsu Research of America Inc., Santa Clara, California, USA"],"raw_orcid":"https://orcid.org/0009-0003-2239-1014","affiliations":[{"raw_affiliation_string":"Fujitsu Research of America Inc., Santa Clara, California, USA","institution_ids":["https://openalex.org/I4210094759"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047561807","display_name":"Shailaja Keyur Sampat","orcid":"https://orcid.org/0009-0006-9873-3342"},"institutions":[{"id":"https://openalex.org/I4210094759","display_name":"Fujitsu (United States)","ror":"https://ror.org/0073whr05","country_code":"US","type":"company","lineage":["https://openalex.org/I2252096349","https://openalex.org/I4210094759"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shailaja Keyur Sampat","raw_affiliation_strings":["Fujitsu Research of America Inc., Santa Clara, California, USA"],"raw_orcid":"https://orcid.org/0009-0006-9873-3342","affiliations":[{"raw_affiliation_string":"Fujitsu Research of America Inc., Santa Clara, California, USA","institution_ids":["https://openalex.org/I4210094759"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043653175","display_name":"Maria Xenochristou","orcid":"https://orcid.org/0000-0001-5064-0813"},"institutions":[{"id":"https://openalex.org/I4210094759","display_name":"Fujitsu (United States)","ror":"https://ror.org/0073whr05","country_code":"US","type":"company","lineage":["https://openalex.org/I2252096349","https://openalex.org/I4210094759"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maria Xenochristou","raw_affiliation_strings":["Fujitsu Research of America Inc., Santa Clara, California, USA"],"raw_orcid":"https://orcid.org/0000-0001-5064-0813","affiliations":[{"raw_affiliation_string":"Fujitsu Research of America Inc., Santa Clara, California, USA","institution_ids":["https://openalex.org/I4210094759"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110714070","display_name":"Wei\u2010Peng Chen","orcid":"https://orcid.org/0009-0006-4351-7415"},"institutions":[{"id":"https://openalex.org/I4210094759","display_name":"Fujitsu (United States)","ror":"https://ror.org/0073whr05","country_code":"US","type":"company","lineage":["https://openalex.org/I2252096349","https://openalex.org/I4210094759"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei-Peng Chen","raw_affiliation_strings":["Fujitsu Research of America Inc., Santa Clara, California, USA"],"raw_orcid":"https://orcid.org/0009-0006-4351-7415","affiliations":[{"raw_affiliation_string":"Fujitsu Research of America Inc., Santa Clara, California, USA","institution_ids":["https://openalex.org/I4210094759"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103511759","display_name":"Takashi Kato","orcid":"https://orcid.org/0009-0007-0097-5923"},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Kato","raw_affiliation_strings":["Fujitsu Research, Kawasaki, Kanagawa, Japan"],"raw_orcid":"https://orcid.org/0009-0007-0097-5923","affiliations":[{"raw_affiliation_string":"Fujitsu Research, Kawasaki, Kanagawa, Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114320338","display_name":"Taisei Kakibuchi","orcid":null},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taisei Kakibuchi","raw_affiliation_strings":["Fujitsu Research, Kawasaki, Kanagawa, Japan"],"raw_orcid":"https://orcid.org/0009-0007-7870-0719","affiliations":[{"raw_affiliation_string":"Fujitsu Research, Kawasaki, Kanagawa, Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103329339","display_name":"Tatsuya Asai","orcid":"https://orcid.org/0009-0003-9708-2929"},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Asai","raw_affiliation_strings":["Fujitsu Research, Kawasaki, Kanagawa, Japan"],"raw_orcid":"https://orcid.org/0009-0003-9708-2929","affiliations":[{"raw_affiliation_string":"Fujitsu Research, Kawasaki, Kanagawa, Japan","institution_ids":["https://openalex.org/I2252096349"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2041","last_page":"2052"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9997000098228455,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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":0.996999979019165,"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/computer-science","display_name":"Computer science","score":0.833315372467041},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4614156186580658},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4428141415119171},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3419939875602722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33471280336380005},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1903383731842041}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.833315372467041},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4614156186580658},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4428141415119171},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3419939875602722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33471280336380005},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1903383731842041}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3691620.3695267","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3691620.3695267","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3691620.3695267","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3691620.3695267","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W246024570","https://openalex.org/W569478347","https://openalex.org/W1973747955","https://openalex.org/W1980265100","https://openalex.org/W2118944554","https://openalex.org/W2131774270","https://openalex.org/W2144211451","https://openalex.org/W2167329753","https://openalex.org/W2341587966","https://openalex.org/W2342249984","https://openalex.org/W2437617937","https://openalex.org/W2743948853","https://openalex.org/W2770230381","https://openalex.org/W2966284335","https://openalex.org/W2968441198","https://openalex.org/W2970476646","https://openalex.org/W2970641574","https://openalex.org/W2991223644","https://openalex.org/W3081464307","https://openalex.org/W3124185882","https://openalex.org/W3137081859","https://openalex.org/W3172642864","https://openalex.org/W3173777717","https://openalex.org/W3174588372","https://openalex.org/W3175111921","https://openalex.org/W3185341429","https://openalex.org/W3194405061","https://openalex.org/W3201904098","https://openalex.org/W4226106502","https://openalex.org/W4243235940","https://openalex.org/W4255268003","https://openalex.org/W6788106616"],"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/W3204019825"],"abstract_inverted_index":{"Data":[0],"wrangling":[1,29,60,111,128],"is":[2],"a":[3,122],"critical":[4],"yet":[5],"often":[6],"labor-intensive":[7],"process,":[8,112],"essential":[9],"for":[10,17,57,108,148],"transforming":[11],"raw":[12],"data":[13,25,28,59,76,99,127,149,174],"into":[14],"formats":[15],"suitable":[16],"downstream":[18,46],"tasks":[19],"such":[20],"as":[21,121],"machine":[22],"learning":[23],"or":[24],"analysis.":[26],"Traditional":[27],"methods":[30],"can":[31],"be":[32],"time-consuming,":[33],"resource-intensive,":[34],"and":[35,42,73,102,115,136,156],"prone":[36],"to":[37,70,96,125,168],"errors,":[38],"limiting":[39],"the":[40,63,92,103,109,144,160,170],"efficiency":[41],"effectiveness":[43,145],"of":[44,65,94,105,146,163,172],"subsequent":[45],"tasks.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,142],"introduce":[52],"AutoDW:":[53],"an":[54],"end-to-end":[55],"solution":[56],"automatic":[58],"that":[61,88],"leverages":[62],"power":[64],"Large":[66],"Language":[67],"Models":[68],"(LLMs)":[69],"enhance":[71],"automation":[72,87],"intelligence":[74],"in":[75,133],"preparation.":[77,175],"AutoDW":[78,147],"distinguishes":[79],"itself":[80],"through":[81],"several":[82],"innovative":[83],"features,":[84],"including":[85],"comprehensive":[86],"minimizes":[89],"human":[90],"intervention,":[91],"integration":[93],"LLMs":[95],"enable":[97],"advanced":[98],"processing":[100],"capabilities,":[101],"generation":[104],"source":[106],"code":[107],"entire":[110],"ensuring":[113],"transparency":[114],"reproducibility.":[116],"These":[117],"advancements":[118],"position":[119],"AuoDW":[120],"superior":[123],"alternative":[124],"existing":[126],"tools,":[129],"offering":[130],"significant":[131],"improvements":[132],"efficiency,":[134],"accuracy,":[135],"flexibility.":[137],"Through":[138],"detailed":[139],"performance":[140],"evaluations,":[141],"demonstrate":[143],"wrangling.":[150],"We":[151],"also":[152],"discuss":[153],"our":[154],"experience":[155],"lessons":[157],"learned":[158],"from":[159],"industrial":[161],"deployment":[162],"AutoDW,":[164],"showcasing":[165],"its":[166],"potential":[167],"transform":[169],"landscape":[171],"automated":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}