{"total":14,"rows":[{"id":"2412.08194","title":"Magneto: Combining Small and Large Language Models for Schema Matching","created":"2024-12-11","cited_by_count":17,"area":null},{"id":"2504.14657","title":"A Case Study Exploring the Current Landscape of Synthetic Medical Record Generation with Commercial LLMs","created":"2025-04-20","cited_by_count":13,"area":null},{"id":"2601.17058","title":"Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs","created":"2026-01-22","cited_by_count":9,"area":null},{"id":"2410.12480","title":"KcMF: A Knowledge-compliant Framework for Schema and Entity Matching with Fine-tuning-free LLMs","created":"2024-10-16","cited_by_count":8,"area":null},{"id":"2508.01556","title":"Empowering Tabular Data Preparation with Language Models: Why and How?","created":"2025-08-03","cited_by_count":4,"area":null},{"id":"2505.24716","title":"Towards Scalable Schema Mapping using Large Language Models","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2605.08687","title":"PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2511.18364","title":"KGpipe: Generation and Evaluation of Pipelines for Data Integration into Knowledge Graphs","created":"2025-11-23","cited_by_count":2,"area":null},{"id":"2512.07246","title":"Ensembling LLM-Induced Decision Trees for Explainable and Robust Error Detection","created":"2025-12-08","cited_by_count":2,"area":null},{"id":"2504.17203","title":"High-Fidelity And Complex Test Data Generation For Google SQL Code Generation Services","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2512.07926","title":"Can AI autonomously build, operate, and use the entire data stack?","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2603.28731","title":"SAGAI-MID: A Generative AI-Driven Middleware for Dynamic Runtime Interoperability","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2608.26750","title":"Discovering Relationships in Data Lakes Using Large Language Models: An Industrial Case","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2610.00907","title":"STEER: Reducing Inference Cost in Relational Foundation Models through Semantically Informed Sampling","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}