{"id":"https://openalex.org/W7164894382","doi":"https://doi.org/10.1109/icdew71238.2026.00037","title":"Automatic End-to-End Data Integration using Large Language Models","display_name":"Automatic End-to-End Data Integration using Large Language Models","publication_year":2026,"publication_date":"2026-05-04","ids":{"openalex":"https://openalex.org/W7164894382","doi":"https://doi.org/10.1109/icdew71238.2026.00037"},"language":"en","primary_location":{"id":"doi:10.1109/icdew71238.2026.00037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdew71238.2026.00037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 42nd International Conference on Data Engineering Workshops (ICDEW)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5128894384","display_name":"Aaron Steiner","orcid":null},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Aaron Steiner","raw_affiliation_strings":["University of Mannheim,Data and Web Science Group,Mannheim,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Mannheim,Data and Web Science Group,Mannheim,Germany","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076876024","display_name":"Christian Bizer","orcid":"https://orcid.org/0000-0003-2367-0237"},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Bizer","raw_affiliation_strings":["University of Mannheim,Data and Web Science Group,Mannheim,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Mannheim,Data and Web Science Group,Mannheim,Germany","institution_ids":["https://openalex.org/I177802217"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177802217"],"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":"142","last_page":"150"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.2492000013589859,"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":0.2492000013589859,"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":0.1054999977350235,"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/T14347","display_name":"Big Data and Digital Economy","score":0.03880000114440918,"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/data-integration","display_name":"Data integration","score":0.5008000135421753},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3391000032424927},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3034000098705292},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.2896000146865845},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.28209999203681946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6726999878883362},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.5008000135421753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4666999876499176},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44020000100135803},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31529998779296875},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2896000146865845},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C33326189","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information integration","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdew71238.2026.00037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdew71238.2026.00037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 42nd International Conference on Data Engineering Workshops (ICDEW)","raw_type":"proceedings-article"},{"id":"pmh:oai:ub-madoc.bib.uni-mannheim.de:72604","is_oa":false,"landing_page_url":"https://orcid.org/0009-0006-6946-7057>","pdf_url":null,"source":{"id":"https://openalex.org/S4377196315","display_name":"MADOC (University of Mannheim)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177802217","host_organization_name":"University of Mannheim","host_organization_lineage":["https://openalex.org/I177802217"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Konferenzver\u00f6ffentlichung"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Designing":[0],"data":[1,10,42,60,87,90,96,103,196],"integration":[2,31,43,61,125],"pipelines":[3,44,118,163,177],"typically":[4],"requires":[5],"substantial":[6],"manual":[7],"effort":[8],"from":[9],"engineers":[11,197],"to":[12,35,66,71,75,113,143],"configure":[13,175],"pipeline":[14,62,74,112,140],"components":[15],"and":[16,94,130,160,170],"label":[17],"training":[18,89],"data.":[19,133],"While":[20],"LLMs":[21],"have":[22],"shown":[23],"promise":[24],"in":[25,102],"handling":[26],"individual":[27],"steps":[28],"of":[29,109,116,126,167,190,193],"the":[30,73,107,114,124,138,154,158,161,173,176,191,199],"process,":[32],"their":[33],"potential":[34],"replace":[36],"all":[37,68],"human":[38,159,195],"input":[39],"across":[40],"end-to-end":[41],"has":[45],"not":[46],"been":[47],"investigated.":[48],"As":[49],"a":[50,187],"step":[51],"toward":[52],"exploring":[53],"this":[54,110],"potential,":[55],"we":[56],"present":[57],"an":[58],"automatic":[59],"that":[63,137],"uses":[64],"GPT-5.2":[65],"generate":[67],"artifacts":[69,80],"required":[70],"adapt":[72],"specific":[76],"use":[77],"cases.":[78],"These":[79],"are":[81],"schema":[82],"mappings,":[83],"value":[84],"mappings":[85],"for":[86,91,97,147],"normalization,":[88],"entity":[92],"matching,":[93],"validation":[95],"selecting":[98],"conflict":[99],"resolution":[100],"heuristics":[101],"fusion.":[104],"We":[105],"compare":[106],"performance":[108,115],"LLM-based":[111,139],"human-designed":[117,155],"along":[119],"three":[120],"case":[121,182],"studies":[122],"requiring":[123],"video":[127],"game,":[128],"music,":[129],"company":[131],"related":[132],"Our":[134],"experiments":[135],"show":[136],"is":[141],"able":[142],"produce":[144,164],"similar":[145],"results,":[146,152],"some":[148],"tasks":[149],"even":[150],"better":[151],"as":[153],"pipelines.":[156],"End-to-end,":[157],"LLM":[162,174],"integrated":[165],"datasets":[166],"comparable":[168],"size":[169],"density.":[171],"Having":[172],"costs":[178],"approximately":[179],"$10":[180],"per":[181],"study,":[183],"which":[184],"represents":[185],"only":[186],"small":[188],"fraction":[189],"cost":[192],"having":[194],"perform":[198],"same":[200],"tasks.":[201]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-06-17T00:00:00"}