CLApr 14, 2025

Abacus-SQL: A Text-to-SQL System Empowering Cross-Domain and Open-Domain Database Retrieval

arXiv:2504.09824v14 citationsh-index: 9ACL
Originality Incremental advance
AI Analysis

This addresses challenges in database querying for users needing automated SQL generation across diverse domains, but it appears incremental as it builds on existing text-to-SQL systems.

The paper tackles the problem of text-to-SQL systems lacking retrieval capabilities for open-domain databases and limited cross-domain transferability, proposing Abacus-SQL which uses database retrieval and data augmentation to achieve excellent performance in multi-turn tasks.

The existing text-to-SQL systems have made significant progress in SQL query generation, but they still face numerous challenges. Existing systems often lack retrieval capabilities for open-domain databases, requiring users to manually filter relevant databases. Additionally, their cross-domain transferability is limited, making it challenging to accommodate diverse query requirements. To address these issues, we propose Abacus-SQL. Abacus-SQL utilizes database retrieval technology to accurately locate the required databases in an open-domain database environment. It also enhances the system cross-domain transfer ability through data augmentation methods. Moreover, Abacus-SQL employs Pre-SQL and Self-debug methods, thereby enhancing the accuracy of SQL queries. Experimental results demonstrate that Abacus-SQL performs excellently in multi-turn text-to-SQL tasks, effectively validating the approach's effectiveness. Abacus-SQL is publicly accessible at https://huozi.8wss.com/abacus-sql/.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes