{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T05:55:48Z","timestamp":1781675748037,"version":"3.54.5"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T00:00:00Z","timestamp":1777852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T00:00:00Z","timestamp":1777852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,4]]},"DOI":"10.1109\/icdew71238.2026.00037","type":"proceedings-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T19:42:37Z","timestamp":1781638957000},"page":"142-150","source":"Crossref","is-referenced-by-count":0,"title":["Automatic End-to-End Data Integration using Large Language Models"],"prefix":"10.1109","author":[{"given":"Aaron","family":"Steiner","sequence":"first","affiliation":[{"name":"University of Mannheim,Data and Web Science Group,Mannheim,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Bizer","sequence":"additional","affiliation":[{"name":"University of Mannheim,Data and Web Science Group,Mannheim,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Principles of Data Integration","author":"Doan","year":"2012"},{"issue":"2","key":"ref2","first-page":"21","article-title":"Data fusion in three steps: Resolving inconsistencies at schema-, tuple-, and value-level","volume":"29","author":"Naumann","year":"2006","journal-title":"IEEE Data Engineering Bulletin"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.14778\/3574245.3574274"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.14778\/1687553.1687620"},{"issue":"1","key":"ref5","first-page":"3","article-title":"Large language models for data discovery and integration: Challenges and opportunities","volume":"49","author":"Freire","year":"2025","journal-title":"IEEE Data Engineering Bulletin"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.14778\/3574245.3574258"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00123"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.14778\/3742728.3742757"},{"key":"ref9","first-page":"529","article-title":"Entity matching using large language models","volume-title":"Proceedings of the 28th International Conference on Extending Database Technology (EDBT)","author":"Peeters"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s007780100057"},{"issue":"3","key":"ref11","first-page":"247","article-title":"Data cleaning: Problems and current approaches","volume":"9","author":"Rahm","year":"2000","journal-title":"The VLDB Journal"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31164-2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1456650.1456651"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-70626-4_15"},{"key":"ref15","first-page":"96","article-title":"Match, compare, or select? an investigation of large language models for entity matching","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics (COLING)","author":"Wang"},{"key":"ref16","article-title":"Kgpipe: Generation and evaluation of pipelines for data integration into knowledge graphs","author":"Hofer","year":"2025"},{"key":"ref17","article-title":"A survey of data agents: Emerging paradigm or overstated hype?","author":"Zhu","year":"2025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.14778\/3748191.3748211"},{"key":"ref19","article-title":"SEED: Simple, efficient, and effective data management via large language models","author":"Chen","year":"2023"},{"key":"ref20","article-title":"Flowetl: An autonomous example-driven pipeline for data engineering","author":"Profio","year":"2025"},{"key":"ref21","article-title":"Dp-bench: A benchmark for evaluating data product creation systems","author":"Chowdhury","year":"2025"},{"key":"ref22","first-page":"28 691","article-title":"Spider 2.0: Evaluating language models on real-world enterprise text-to-sql workflows","volume-title":"International Conference on Learning Representations (ICLR)","author":"Lei"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.14778\/3773749.3773750"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.14778\/3476249.3476303"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2025.102660"},{"key":"ref26","article-title":"Interactive data harmonization with llm agents: Opportunities and challenges","author":"Santos","year":"2025"}],"event":{"name":"2026 IEEE 42nd International Conference on Data Engineering Workshops (ICDEW)","location":"Montreal, QC, Canada","start":{"date-parts":[[2026,5,4]]},"end":{"date-parts":[[2026,5,8]]}},"container-title":["2026 IEEE 42nd International Conference on Data Engineering Workshops (ICDEW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11558595\/11558596\/11558764.pdf?arnumber=11558764","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T05:26:21Z","timestamp":1781673981000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11558764\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,4]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icdew71238.2026.00037","relation":{},"subject":[],"published":{"date-parts":[[2026,5,4]]}}}