Dubo-SQL: Diverse Retrieval-Augmented Generation and Fine Tuning for Text-to-SQL

arXiv:2404.12560v1 Announce Type: new
Abstract: The current state-of-the-art (SOTA) for automated text-to-SQL still falls well short of expert human performance as measured by execution accuracy (EX) on the BIRD-SQL benchmark. The most accurate methods are also slow and expensive. To advance the SOTA for text-to-SQL while reducing cost and improving speed, we explore the combination of low-cost fine tuning, novel methods for diverse retrieval-augmented generation (RAG) and new input and output formats that help large language models (LLMs) achieve higher …

abstract accuracy advance art arxiv automated benchmark bird cost cs.cl cs.db current diverse expert human human performance improving performance retrieval retrieval-augmented sota speed sql state text text-to-sql type