Lucy: Think and Reason to Solve Text-to-SQL
This addresses a critical bottleneck for users querying complex enterprise databases, offering a significant improvement over existing methods.
The paper tackles the problem of LLMs performing poorly on large enterprise databases with many tables and complex relationships, proposing a framework that combines LLMs with automated reasoning to achieve state-of-the-art zero-shot text-to-SQL results on complex benchmarks.
Large Language Models (LLMs) have made significant progress in assisting users to query databases in natural language. While LLM-based techniques provide state-of-the-art results on many standard benchmarks, their performance significantly drops when applied to large enterprise databases. The reason is that these databases have a large number of tables with complex relationships that are challenging for LLMs to reason about. We analyze challenges that LLMs face in these settings and propose a new solution that combines the power of LLMs in understanding questions with automated reasoning techniques to handle complex database constraints. Based on these ideas, we have developed a new framework that outperforms state-of-the-art techniques in zero-shot text-to-SQL on complex benchmarks