DCG-SQL: Enhancing In-Context Learning for Text-to-SQL with Deep Contextual Schema Link Graph
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908460081217536 |
|---|---|
| author | Lee, Jihyung Lee, Jin-Seop Lee, Jaehoon Choi, YunSeok Lee, Jee-Hyong |
| author_facet | Lee, Jihyung Lee, Jin-Seop Lee, Jaehoon Choi, YunSeok Lee, Jee-Hyong |
| contents | Text-to-SQL, which translates a natural language question into an SQL query, has advanced with in-context learning of Large Language Models (LLMs). However, existing methods show little improvement in performance compared to randomly chosen demonstrations, and significant performance drops when smaller LLMs (e.g., Llama 3.1-8B) are used. This indicates that these methods heavily rely on the intrinsic capabilities of hyper-scaled LLMs, rather than effectively retrieving useful demonstrations. In this paper, we propose a novel approach for effectively retrieving demonstrations and generating SQL queries. We construct a Deep Contextual Schema Link Graph, which contains key information and semantic relationship between a question and its database schema items. This graph-based structure enables effective representation of Text-to-SQL samples and retrieval of useful demonstrations for in-context learning. Experimental results on the Spider benchmark demonstrate the effectiveness of our approach, showing consistent improvements in SQL generation performance and efficiency across both hyper-scaled LLMs and small LLMs. The code is available at https://github.com/jjklle/DCG-SQL}{https://github.com/jjklle/DCG-SQL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19956 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DCG-SQL: Enhancing In-Context Learning for Text-to-SQL with Deep Contextual Schema Link Graph Lee, Jihyung Lee, Jin-Seop Lee, Jaehoon Choi, YunSeok Lee, Jee-Hyong Artificial Intelligence Computation and Language Text-to-SQL, which translates a natural language question into an SQL query, has advanced with in-context learning of Large Language Models (LLMs). However, existing methods show little improvement in performance compared to randomly chosen demonstrations, and significant performance drops when smaller LLMs (e.g., Llama 3.1-8B) are used. This indicates that these methods heavily rely on the intrinsic capabilities of hyper-scaled LLMs, rather than effectively retrieving useful demonstrations. In this paper, we propose a novel approach for effectively retrieving demonstrations and generating SQL queries. We construct a Deep Contextual Schema Link Graph, which contains key information and semantic relationship between a question and its database schema items. This graph-based structure enables effective representation of Text-to-SQL samples and retrieval of useful demonstrations for in-context learning. Experimental results on the Spider benchmark demonstrate the effectiveness of our approach, showing consistent improvements in SQL generation performance and efficiency across both hyper-scaled LLMs and small LLMs. The code is available at https://github.com/jjklle/DCG-SQL}{https://github.com/jjklle/DCG-SQL. |
| title | DCG-SQL: Enhancing In-Context Learning for Text-to-SQL with Deep Contextual Schema Link Graph |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2505.19956 |