SchemaGraphSQL: Efficient Schema Linking with Pathfinding Graph Algorithms for Text-to-SQL on Large-Scale Databases
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915303199342592 |
|---|---|
| author | Safdarian, AmirHossein Mohammadi, Milad Jahanbakhsh, Ehsan Naderi, Mona Shahamat Faili, Heshaam |
| author_facet | Safdarian, AmirHossein Mohammadi, Milad Jahanbakhsh, Ehsan Naderi, Mona Shahamat Faili, Heshaam |
| contents | Text-to-SQL systems translate natural language questions into executable SQL queries, and recent progress with large language models (LLMs) has driven substantial improvements in this task. Schema linking remains a critical component in Text-to-SQL systems, reducing prompt size for models with narrow context windows and sharpening model focus even when the entire schema fits. We present a zero-shot, training-free schema linking approach that first constructs a schema graph based on foreign key relations, then uses a single prompt to Gemini 2.5 Flash to extract source and destination tables from the user query, followed by applying classical path-finding algorithms and post-processing to identify the optimal sequence of tables and columns that should be joined, enabling the LLM to generate more accurate SQL queries. Despite being simple, cost-effective, and highly scalable, our method achieves state-of-the-art results on the BIRD benchmark, outperforming previous specialized, fine-tuned, and complex multi-step LLM-based approaches. We conduct detailed ablation studies to examine the precision-recall trade-off in our framework. Additionally, we evaluate the execution accuracy of our schema filtering method compared to other approaches across various model sizes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_18363 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SchemaGraphSQL: Efficient Schema Linking with Pathfinding Graph Algorithms for Text-to-SQL on Large-Scale Databases Safdarian, AmirHossein Mohammadi, Milad Jahanbakhsh, Ehsan Naderi, Mona Shahamat Faili, Heshaam Computation and Language Artificial Intelligence Databases Text-to-SQL systems translate natural language questions into executable SQL queries, and recent progress with large language models (LLMs) has driven substantial improvements in this task. Schema linking remains a critical component in Text-to-SQL systems, reducing prompt size for models with narrow context windows and sharpening model focus even when the entire schema fits. We present a zero-shot, training-free schema linking approach that first constructs a schema graph based on foreign key relations, then uses a single prompt to Gemini 2.5 Flash to extract source and destination tables from the user query, followed by applying classical path-finding algorithms and post-processing to identify the optimal sequence of tables and columns that should be joined, enabling the LLM to generate more accurate SQL queries. Despite being simple, cost-effective, and highly scalable, our method achieves state-of-the-art results on the BIRD benchmark, outperforming previous specialized, fine-tuned, and complex multi-step LLM-based approaches. We conduct detailed ablation studies to examine the precision-recall trade-off in our framework. Additionally, we evaluate the execution accuracy of our schema filtering method compared to other approaches across various model sizes. |
| title | SchemaGraphSQL: Efficient Schema Linking with Pathfinding Graph Algorithms for Text-to-SQL on Large-Scale Databases |
| topic | Computation and Language Artificial Intelligence Databases |
| url | https://arxiv.org/abs/2505.18363 |