AI RESEARCH

EvoSchema: Towards Text-to-SQL Robustness Against Schema Evolution

arXiv CS.AI

ArXi:2603.10697v1 Announce Type: cross Neural text-to-SQL models, which translate natural language questions (NLQs) into SQL queries given a database schema, have achieved remarkable performance. However, database schemas frequently evolve to meet new requirements. Such schema evolution often leads to performance degradation for models trained on static schemas.