CRED-SQL: Enhancing Real-world Large Scale Database Text-to-SQL Parsing through Cluster Retrieval and Execution Description
Year: 2025
Type: preprint
Abstract: Recent advances in large language models (LLMs) have significantly improved the accuracy of Text-to-SQL systems. However, a critical challenge remains: the semantic mismatch between natural language questions (NLQs) and their corresponding SQL queries. This issue is exacerbated in large-scale databases, where semantically similar attributes hinder schema linking and semantic drift during SQL generation, ultimately reducing model accuracy. To address these challenges, we introduce CRED-SQL, a framework designed for large-scale databases that integrates Cluster Retrieval and Execution Description. CRED-SQL first performs cluster-based large-scale schema retrieval to pinpoint the tables and columns most relevant to a given NLQ, alleviating schema mismatch. It then introduces an intermediate natural language representation-Execution Description Language (EDL)-to bridge the gap between NLQs and SQL. This reformulation decomposes the task into two stages: Text-to-EDL and EDL-to-SQL, leveraging LLMs' strong general reasoning capabilities while reducing semantic deviation. Extensive experiments on two large-scale, cross-domain benchmarks-SpiderUnion and BirdUnion-demonstrate that CRED-SQL achieves new state-of-the-art (SOTA) performance, validating its effectiveness and scalability. Our code is available at https://github.com/smduan/CRED-SQL.git
Source: arXiv (Cornell University)
Authors: Duan, Shaoming, Wang, Zirui, Liu, Chuanyi, Zhu, Zhibin, Zhang, Yuhao, Han, Peiyi, Yan, Liang, Peng, Zewu
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7076158140
Cites:
Cited by:
Related to: