From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems
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_ | 1866913676209946624 |
|---|---|
| author | Mohammadjafari, Ali Maida, Anthony S. Gottumukkala, Raju |
| author_facet | Mohammadjafari, Ali Maida, Anthony S. Gottumukkala, Raju |
| contents | LLMs when used with Retrieval Augmented Generation (RAG), are greatly improving the SOTA of translating natural language queries to structured and correct SQL. Unlike previous reviews, this survey provides a comprehensive study of the evolution of LLM-based text-to-SQL systems, from early rule-based models to advanced LLM approaches that use (RAG) systems. We discuss benchmarks, evaluation methods, and evaluation metrics. Also, we uniquely study the use of Graph RAGs for better contextual accuracy and schema linking in these systems. Finally, we highlight key challenges such as computational efficiency, model robustness, and data privacy toward improvements of LLM-based text-to-SQL systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_01066 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems Mohammadjafari, Ali Maida, Anthony S. Gottumukkala, Raju Computation and Language Artificial Intelligence LLMs when used with Retrieval Augmented Generation (RAG), are greatly improving the SOTA of translating natural language queries to structured and correct SQL. Unlike previous reviews, this survey provides a comprehensive study of the evolution of LLM-based text-to-SQL systems, from early rule-based models to advanced LLM approaches that use (RAG) systems. We discuss benchmarks, evaluation methods, and evaluation metrics. Also, we uniquely study the use of Graph RAGs for better contextual accuracy and schema linking in these systems. Finally, we highlight key challenges such as computational efficiency, model robustness, and data privacy toward improvements of LLM-based text-to-SQL systems. |
| title | From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2410.01066 |