SchemaGraphSQL: Efficient Schema Linking with Pathfinding Graph Algorithms for Text-to-SQL on Large-Scale Databases

TL;DR

SchemaGraphSQL introduces a zero-shot, training-free schema linking method using graph algorithms, significantly improving Text-to-SQL accuracy on large databases with a simple, scalable approach that outperforms complex models.

Contribution

The paper proposes a novel, cost-effective schema linking technique using pathfinding algorithms, eliminating the need for training and enhancing large-scale Text-to-SQL performance.

Findings

Achieves state-of-the-art results on the BIRD benchmark.

Outperforms fine-tuned and complex multi-step LLM approaches.

Demonstrates high scalability and effectiveness across model sizes.

Abstract

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.