Saved in:
Bibliographic Details
Main Authors: Narodytska, Nina, Vargaftik, Shay
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.05153
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910516148961280
author Narodytska, Nina
Vargaftik, Shay
author_facet Narodytska, Nina
Vargaftik, Shay
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2407_05153
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Lucy: Think and Reason to Solve Text-to-SQL
Narodytska, Nina
Vargaftik, Shay
Artificial Intelligence
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
title Lucy: Think and Reason to Solve Text-to-SQL
topic Artificial Intelligence
url https://arxiv.org/abs/2407.05153