Lucy:通过思考与推理解决 Text-to-SQL 问题
Lucy: Think and Reason to Solve Text-to-SQL
AI总结:
针对大型企业数据库中表多、关系复杂导致 LLM 的 Text-to-SQL 性能下降问题,提出融合 LLM 问题理解与自动推理约束处理的 Lucy 框架,并在零样本复杂基准上超越现有方法。
摘要:
大语言模型(LLM)在帮助用户使用自然语言查询数据库方面已取得显著进展。尽管基于 LLM 的技术在许多标准基准测试上提供了最先进的结果,但当应用于大型企业数据库时,其性能会显著下降。原因在于这些数据库包含大量表,且表间关系复杂,使 LLM 难以进行推理。我们分析了 LLM 在这些场景下面临的挑战,并提出一种新的解决方案:将 LLM 理解问题的能力与自动推理技术相结合,以处理复杂的数据库约束。基于这些想法,我们开发了一个新框架,在复杂基准测试的零样本 Text-to-SQL 任务上优于最先进技术。
英文摘要:
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
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。