Text-to-SQL based on Large Language Models and Database Keyword Search
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917900688818176 |
|---|---|
| author | Nascimento, Eduardo R. Avila, Caio Viktor S. Izquierdo, Yenier T. García, Grettel M. Andrade, Lucas Feijó L. Facina, Michelle S. P. Lemos, Melissa Casanova, Marco A. |
| author_facet | Nascimento, Eduardo R. Avila, Caio Viktor S. Izquierdo, Yenier T. García, Grettel M. Andrade, Lucas Feijó L. Facina, Michelle S. P. Lemos, Melissa Casanova, Marco A. |
| contents | Text-to-SQL prompt strategies based on Large Language Models (LLMs) achieve remarkable performance on well-known benchmarks. However, when applied to real-world databases, their performance is significantly less than for these benchmarks, especially for Natural Language (NL) questions requiring complex filters and joins to be processed. This paper then proposes a strategy to compile NL questions into SQL queries that incorporates a dynamic few-shot examples strategy and leverages the services provided by a database keyword search (KwS) platform. The paper details how the precision and recall of the schema-linking process are improved with the help of the examples provided and the keyword-matching service that the KwS platform offers. Then, it shows how the KwS platform can be used to synthesize a view that captures the joins required to process an input NL question and thereby simplify the SQL query compilation step. The paper includes experiments with a real-world relational database to assess the performance of the proposed strategy. The experiments suggest that the strategy achieves an accuracy on the real-world relational database that surpasses state-of-the-art approaches. The paper concludes by discussing the results obtained. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_13594 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Text-to-SQL based on Large Language Models and Database Keyword Search Nascimento, Eduardo R. Avila, Caio Viktor S. Izquierdo, Yenier T. García, Grettel M. Andrade, Lucas Feijó L. Facina, Michelle S. P. Lemos, Melissa Casanova, Marco A. Databases Artificial Intelligence 68T50 H.2.3; I.2.7 Text-to-SQL prompt strategies based on Large Language Models (LLMs) achieve remarkable performance on well-known benchmarks. However, when applied to real-world databases, their performance is significantly less than for these benchmarks, especially for Natural Language (NL) questions requiring complex filters and joins to be processed. This paper then proposes a strategy to compile NL questions into SQL queries that incorporates a dynamic few-shot examples strategy and leverages the services provided by a database keyword search (KwS) platform. The paper details how the precision and recall of the schema-linking process are improved with the help of the examples provided and the keyword-matching service that the KwS platform offers. Then, it shows how the KwS platform can be used to synthesize a view that captures the joins required to process an input NL question and thereby simplify the SQL query compilation step. The paper includes experiments with a real-world relational database to assess the performance of the proposed strategy. The experiments suggest that the strategy achieves an accuracy on the real-world relational database that surpasses state-of-the-art approaches. The paper concludes by discussing the results obtained. |
| title | Text-to-SQL based on Large Language Models and Database Keyword Search |
| topic | Databases Artificial Intelligence 68T50 H.2.3; I.2.7 |
| url | https://arxiv.org/abs/2501.13594 |