{"id":"https://openalex.org/W7135075826","doi":"https://doi.org/10.48550/arxiv.2603.10547","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":"2026-03-11","ids":{"openalex":"https://openalex.org/W7135075826","doi":"https://doi.org/10.48550/arxiv.2603.10547"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.10547","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10547","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.10547","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128894384","display_name":"Aaron Steiner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steiner, Aaron","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076876024","display_name":"Christian Bizer","orcid":"https://orcid.org/0000-0003-2367-0237"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bizer, Christian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.33009999990463257,"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":0.33009999990463257,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.06260000169277191,"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":0.05950000137090683,"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/pipeline","display_name":"Pipeline (software)","score":0.7921000123023987},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.7218999862670898},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.6883000135421753},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6413000226020813},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4032000005245209},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.32580000162124634},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.32269999384880066},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.3192000091075897}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7921000123023987},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.7218999862670898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6953999996185303},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.6883000135421753},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6413000226020813},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.534500002861023},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4032000005245209},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.32269999384880066},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C19527686","wikidata":"https://www.wikidata.org/wiki/Q1665453","display_name":"System integration","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C33326189","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information integration","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C80344994","wikidata":"https://www.wikidata.org/wiki/Q5227369","display_name":"Data virtualization","level":4,"score":0.29120001196861267},{"id":"https://openalex.org/C92446256","wikidata":"https://www.wikidata.org/wiki/Q3306762","display_name":"Data validation","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27059999108314514},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C13926793","wikidata":"https://www.wikidata.org/wiki/Q3507155","display_name":"Group method of data handling","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2597000002861023},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.10547","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10547","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.10547","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10547","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"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":"2026-07-01T06:00:48.157686","created_date":"2026-03-13T00:00:00"}