{"total":24,"rows":[{"id":"2312.01678","title":"Jellyfish: A Large Language Model for Data Preprocessing","created":"2023-12-04","cited_by_count":20,"area":null},{"id":"2409.08185","title":"Fine-tuning Large Language Models for Entity Matching","created":"2024-09-12","cited_by_count":16,"area":null},{"id":"2312.03987","title":"Cost-Effective In-Context Learning for Entity Resolution: A Design Space Exploration","created":"2023-12-07","cited_by_count":15,"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":"2405.15122","title":"Generalizable and Scalable Multistage Biomedical Concept Normalization Leveraging Large Language Models","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2603.10547","title":"Automatic End-to-End Data Integration using Large Language Models","created":"2026-03-11","cited_by_count":3,"area":null},{"id":"2505.14918","title":"Reliable Decision Support with LLMs: A Framework for Evaluating Consistency in Binary Text Classification Applications","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2511.06300","title":"3dSAGER: Geospatial Entity Resolution over 3D Objects (Technical Report)","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2601.21138","title":"EnsembleLink: Accurate Record Linkage Without Training Data","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2606.24407","title":"Entity Resolution via Batched Oracle Queries","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2606.30371","title":"MaDI-Bench: An End-to-End Data Integration Benchmark","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2502.10453","title":"Linking Cryptoasset Attribution Tags to Knowledge Graph Entities: An LLM-based Approach","created":"2025-02-12","cited_by_count":0,"area":null},{"id":"2504.15261","title":"Leveraging Language Models for Automated Patient Record Linkage","created":"2025-04-21","cited_by_count":0,"area":null},{"id":"2507.11086","title":"Beyond Traditional Algorithms: Leveraging LLMs for Accurate Cross-Border Entity Identification","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2509.15858","title":"Optimizing Product Deduplication in E-Commerce with Multimodal Embeddings","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2603.11051","title":"OpenSanctions Pairs: Large-Scale Entity Matching with LLMs","created":"2026-02-24","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":"2607.20694","title":"Attribution Markets: A Fisher-Market Formulation for Fractional Credit Assignment Between Planned Tasks and Performed Actions","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2607.25215","title":"Leveraging Semantic Maps for City-Scale Cross-View Localization","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2607.26298","title":"Entity Resolution in Practice: Lessons from a Self-Serve Pipeline","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.24218","title":"Constraint-Guided Enterprise Data Mapping with Large Language Models","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.04269","title":"Corporate-Family Resolution Is Not a String-Matching Problem: A Public Benchmark Stratified by Name Visibility","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.33878","title":"Curating Merchant-Matching Training Data with Two Confidence-Gated Local LLM Judges","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.37713","title":"Billiger.de Products: A Bilingual Entity Matching Benchmark","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}