QDA-SQL: Questions Enhanced Dialogue Augmentation for Multi-Turn Text-to-SQL
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_ | 1866929584920854528 |
|---|---|
| author | Sun, Yinggang Guo, Ziming Yu, Haining Liu, Chuanyi Li, Xiang Wang, Bingxuan Yu, Xiangzhan Zhao, Tiancheng |
| author_facet | Sun, Yinggang Guo, Ziming Yu, Haining Liu, Chuanyi Li, Xiang Wang, Bingxuan Yu, Xiangzhan Zhao, Tiancheng |
| contents | Fine-tuning large language models (LLMs) for specific domain tasks has achieved great success in Text-to-SQL tasks. However, these fine-tuned models often face challenges with multi-turn Text-to-SQL tasks caused by ambiguous or unanswerable questions. It is desired to enhance LLMs to handle multiple types of questions in multi-turn Text-to-SQL tasks. To address this, we propose a novel data augmentation method, called QDA-SQL, which generates multiple types of multi-turn Q\&A pairs using LLMs. In QDA-SQL, we introduce a method incorporating validation and correction mechanisms to handle complex multi-turn Text-to-SQL tasks. Experimental results demonstrate that QDA-SQL enables fine-tuned models to exhibit higher performance on SQL statement accuracy and enhances their ability to handle complex, unanswerable questions in multi-turn Text-to-SQL tasks. The generation script and test set are released at https://github.com/mcxiaoxiao/QDA-SQL |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_10593 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | QDA-SQL: Questions Enhanced Dialogue Augmentation for Multi-Turn Text-to-SQL Sun, Yinggang Guo, Ziming Yu, Haining Liu, Chuanyi Li, Xiang Wang, Bingxuan Yu, Xiangzhan Zhao, Tiancheng Artificial Intelligence Databases Information Retrieval Fine-tuning large language models (LLMs) for specific domain tasks has achieved great success in Text-to-SQL tasks. However, these fine-tuned models often face challenges with multi-turn Text-to-SQL tasks caused by ambiguous or unanswerable questions. It is desired to enhance LLMs to handle multiple types of questions in multi-turn Text-to-SQL tasks. To address this, we propose a novel data augmentation method, called QDA-SQL, which generates multiple types of multi-turn Q\&A pairs using LLMs. In QDA-SQL, we introduce a method incorporating validation and correction mechanisms to handle complex multi-turn Text-to-SQL tasks. Experimental results demonstrate that QDA-SQL enables fine-tuned models to exhibit higher performance on SQL statement accuracy and enhances their ability to handle complex, unanswerable questions in multi-turn Text-to-SQL tasks. The generation script and test set are released at https://github.com/mcxiaoxiao/QDA-SQL |
| title | QDA-SQL: Questions Enhanced Dialogue Augmentation for Multi-Turn Text-to-SQL |
| topic | Artificial Intelligence Databases Information Retrieval |
| url | https://arxiv.org/abs/2406.10593 |