ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qin, Yang, Chen, Chao, Fu, Zhihang, Chen, Ze, Peng, Dezhong, Hu, Peng, Ye, Jieping
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910968281300992
author Qin, Yang
Chen, Chao
Fu, Zhihang
Chen, Ze
Peng, Dezhong
Hu, Peng
Ye, Jieping
author_facet Qin, Yang
Chen, Chao
Fu, Zhihang
Chen, Ze
Peng, Dezhong
Hu, Peng
Ye, Jieping
contents Despite the significant advancements in Text-to-SQL (Text2SQL) facilitated by large language models (LLMs), the latest state-of-the-art techniques are still trapped in the in-context learning of closed-source LLMs (e.g., GPT-4), which limits their applicability in open scenarios. To address this challenge, we propose a novel RObust mUltitask Tuning and collaboration mEthod (ROUTE) to improve the comprehensive capabilities of open-source LLMs for Text2SQL, thereby providing a more practical solution. Our approach begins with multi-task supervised fine-tuning (SFT) using various synthetic training data related to SQL generation. Unlike existing SFT-based Text2SQL methods, we introduced several additional SFT tasks, including schema linking, noise correction, and continuation writing. Engaging in a variety of SQL generation tasks enhances the model's understanding of SQL syntax and improves its ability to generate high-quality SQL queries. Additionally, inspired by the collaborative modes of LLM agents, we introduce a Multitask Collaboration Prompting (MCP) strategy. This strategy leverages collaboration across several SQL-related tasks to reduce hallucinations during SQL generation, thereby maximizing the potential of enhancing Text2SQL performance through explicit multitask capabilities. Extensive experiments and in-depth analyses have been performed on eight open-source LLMs and five widely-used benchmarks. The results demonstrate that our proposal outperforms the latest Text2SQL methods and yields leading performance.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10138
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL
Qin, Yang
Chen, Chao
Fu, Zhihang
Chen, Ze
Peng, Dezhong
Hu, Peng
Ye, Jieping
Computation and Language
Artificial Intelligence
Despite the significant advancements in Text-to-SQL (Text2SQL) facilitated by large language models (LLMs), the latest state-of-the-art techniques are still trapped in the in-context learning of closed-source LLMs (e.g., GPT-4), which limits their applicability in open scenarios. To address this challenge, we propose a novel RObust mUltitask Tuning and collaboration mEthod (ROUTE) to improve the comprehensive capabilities of open-source LLMs for Text2SQL, thereby providing a more practical solution. Our approach begins with multi-task supervised fine-tuning (SFT) using various synthetic training data related to SQL generation. Unlike existing SFT-based Text2SQL methods, we introduced several additional SFT tasks, including schema linking, noise correction, and continuation writing. Engaging in a variety of SQL generation tasks enhances the model's understanding of SQL syntax and improves its ability to generate high-quality SQL queries. Additionally, inspired by the collaborative modes of LLM agents, we introduce a Multitask Collaboration Prompting (MCP) strategy. This strategy leverages collaboration across several SQL-related tasks to reduce hallucinations during SQL generation, thereby maximizing the potential of enhancing Text2SQL performance through explicit multitask capabilities. Extensive experiments and in-depth analyses have been performed on eight open-source LLMs and five widely-used benchmarks. The results demonstrate that our proposal outperforms the latest Text2SQL methods and yields leading performance.
title ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2412.10138