SQLfuse: Enhancing Text-to-SQL Performance through Comprehensive LLM Synergy
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909262895120384 |
|---|---|
| author | Zhang, Tingkai Chen, Chaoyu Liao, Cong Wang, Jun Zhao, Xudong Yu, Hang Wang, Jianchao Li, Jianguo Shi, Wenhui |
| author_facet | Zhang, Tingkai Chen, Chaoyu Liao, Cong Wang, Jun Zhao, Xudong Yu, Hang Wang, Jianchao Li, Jianguo Shi, Wenhui |
| contents | Text-to-SQL conversion is a critical innovation, simplifying the transition from complex SQL to intuitive natural language queries, especially significant given SQL's prevalence in the job market across various roles. The rise of Large Language Models (LLMs) like GPT-3.5 and GPT-4 has greatly advanced this field, offering improved natural language understanding and the ability to generate nuanced SQL statements. However, the potential of open-source LLMs in Text-to-SQL applications remains underexplored, with many frameworks failing to leverage their full capabilities, particularly in handling complex database queries and incorporating feedback for iterative refinement. Addressing these limitations, this paper introduces SQLfuse, a robust system integrating open-source LLMs with a suite of tools to enhance Text-to-SQL translation's accuracy and usability. SQLfuse features four modules: schema mining, schema linking, SQL generation, and a SQL critic module, to not only generate but also continuously enhance SQL query quality. Demonstrated by its leading performance on the Spider Leaderboard and deployment by Ant Group, SQLfuse showcases the practical merits of open-source LLMs in diverse business contexts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_14568 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SQLfuse: Enhancing Text-to-SQL Performance through Comprehensive LLM Synergy Zhang, Tingkai Chen, Chaoyu Liao, Cong Wang, Jun Zhao, Xudong Yu, Hang Wang, Jianchao Li, Jianguo Shi, Wenhui Computation and Language Artificial Intelligence Databases Text-to-SQL conversion is a critical innovation, simplifying the transition from complex SQL to intuitive natural language queries, especially significant given SQL's prevalence in the job market across various roles. The rise of Large Language Models (LLMs) like GPT-3.5 and GPT-4 has greatly advanced this field, offering improved natural language understanding and the ability to generate nuanced SQL statements. However, the potential of open-source LLMs in Text-to-SQL applications remains underexplored, with many frameworks failing to leverage their full capabilities, particularly in handling complex database queries and incorporating feedback for iterative refinement. Addressing these limitations, this paper introduces SQLfuse, a robust system integrating open-source LLMs with a suite of tools to enhance Text-to-SQL translation's accuracy and usability. SQLfuse features four modules: schema mining, schema linking, SQL generation, and a SQL critic module, to not only generate but also continuously enhance SQL query quality. Demonstrated by its leading performance on the Spider Leaderboard and deployment by Ant Group, SQLfuse showcases the practical merits of open-source LLMs in diverse business contexts. |
| title | SQLfuse: Enhancing Text-to-SQL Performance through Comprehensive LLM Synergy |
| topic | Computation and Language Artificial Intelligence Databases |
| url | https://arxiv.org/abs/2407.14568 |