paper-with-me

Papers

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

2025-05-23 · AmirHossein Safdarian, Milad Mohammadi, Ehsan Jahanbakhsh, Mona Shahamat Naderi, Heshaam Faili

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.

📄 PDF Abstract BibTeX arXiv:2505.18363

Code (0)

등록된 구현이 없습니다.

Tasks

Text to SQLText-To-SQL

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Semantic Enhanced Text-to-SQL Parsing via Iteratively Learning Schema Linking Graph

2022-08-08 · Aiwei Liu, Xuming Hu, Li Lin, Lijie Wen

The generalizability to new databases is of vital importance to Text-to-SQL systems which aim to parse human utterances into SQL statements. Existing works achieve this goal by leveraging the exact matching method to ide…

Graph LearningSQL ParsingText to SQLText-To-SQL

Extractive Schema Linking for Text-to-SQL

2025-01-23 · Michael Glass, Mustafa Eyceoz, Dharmashankar Subramanian, Gaetano Rossiello 외

Text-to-SQL is emerging as a practical interface for real world databases. The dominant paradigm for Text-to-SQL is cross-database or schema-independent, supporting application schemas unseen during training. The schema …

Text to SQLText-To-SQL

SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL

2021-11-01 · NeurIPS 2021 12 · Ruichu Cai, Jinjie Yuan, Boyan Xu, Zhifeng Hao

The Text-to-SQL task, aiming to translate the natural language of the questions into SQL queries, has drawn much attention recently. One of the most challenging problems of Text-to-SQL is how to generalize the trained mo…

Semantic ParsingText to SQLText-To-SQL

Re-examining the Role of Schema Linking in Text-to-SQL

2020-11-01 · EMNLP 2020 11 · Wenqiang Lei, Weixin Wang, Zhixin Ma, Tian Gan 외

In existing sophisticated text-to-SQL models, schema linking is often considered as a simple, minor component, belying its importance. By providing a schema linking corpus based on the Spider text-to-SQL dataset, we syst…

Text to SQLText-To-SQL

Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generation

2025-02-18 · Zheng Yuan, Hao Chen, Zijin Hong, Qinggang Zhang 외

Generating SQLs from user queries is a long-standing challenge, where the accuracy of initial schema linking significantly impacts subsequent SQL generation performance. However, current schema linking models still strug…

Text to SQLText-To-SQL