RB-SQL: A Retrieval-based LLM Framework for Text-to-SQL
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910523739602944 |
|---|---|
| author | Wu, Zhenhe Li, Zhongqiu Zhang, Jie Li, Mengxiang Zhao, Yu Fang, Ruiyu He, Zhongjiang Li, Xuelong Li, Zhoujun Song, Shuangyong |
| author_facet | Wu, Zhenhe Li, Zhongqiu Zhang, Jie Li, Mengxiang Zhao, Yu Fang, Ruiyu He, Zhongjiang Li, Xuelong Li, Zhoujun Song, Shuangyong |
| contents | Large language models (LLMs) with in-context learning have significantly improved the performance of text-to-SQL task. Previous works generally focus on using exclusive SQL generation prompt to improve the LLMs' reasoning ability. However, they are mostly hard to handle large databases with numerous tables and columns, and usually ignore the significance of pre-processing database and extracting valuable information for more efficient prompt engineering. Based on above analysis, we propose RB-SQL, a novel retrieval-based LLM framework for in-context prompt engineering, which consists of three modules that retrieve concise tables and columns as schema, and targeted examples for in-context learning. Experiment results demonstrate that our model achieves better performance than several competitive baselines on public datasets BIRD and Spider. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_08273 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RB-SQL: A Retrieval-based LLM Framework for Text-to-SQL Wu, Zhenhe Li, Zhongqiu Zhang, Jie Li, Mengxiang Zhao, Yu Fang, Ruiyu He, Zhongjiang Li, Xuelong Li, Zhoujun Song, Shuangyong Computation and Language Large language models (LLMs) with in-context learning have significantly improved the performance of text-to-SQL task. Previous works generally focus on using exclusive SQL generation prompt to improve the LLMs' reasoning ability. However, they are mostly hard to handle large databases with numerous tables and columns, and usually ignore the significance of pre-processing database and extracting valuable information for more efficient prompt engineering. Based on above analysis, we propose RB-SQL, a novel retrieval-based LLM framework for in-context prompt engineering, which consists of three modules that retrieve concise tables and columns as schema, and targeted examples for in-context learning. Experiment results demonstrate that our model achieves better performance than several competitive baselines on public datasets BIRD and Spider. |
| title | RB-SQL: A Retrieval-based LLM Framework for Text-to-SQL |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2407.08273 |