Bridging Global Intent with Local Details: A Hierarchical Representation Approach for Semantic Validation in Text-to-SQL

Rihong Qiu, Zhibang Yang, Xinke Jiang, Weibin Liao, Xin Gao, Xu Chu, Junfeng Zhao, Yasha Wang

Keywords: Text-to-SQL Semantic Validation, Hierarchical SQL Representation, AST-driven sub-SQL augmentation

Abstract:

Text-to-SQL translates natural language questions into SQL statements grounded in a target database schema. Ensuring the reliability and executability of such systems requires validating generated SQL—but most existing approaches focus only on syntactic correctness, with few addressing semantic validation (detecting misalignments between questions and SQL). As a consequence, how to achieve effective semantic validation still faces two key challenges: capturing both global user intent and SQL structural details, and constructing high-quality fine-grained sub-SQL annotations.
To tackle these, we introduce HeroSQL, a hierarchical SQL representation approach that integrates global intent (via Logical Plans, LPs) and local details (via Abstract Syntax Trees, ASTs).
To establish better information propagation, we further employ a Nested Message Passing Neural Network (NMPNN) to capture inherent relational information in SQL and aggregate schema-guided semantics across LPs and ASTs.
Additionally, to generate high-quality negative samples, we propose an AST-driven sub-SQL augmentation strategy, supporting robust optimization of fine-grained semantic inconsistencies.
Extensive experiments conducted on Text-to-SQL validation benchmarks (in-domain and out-of-domain settings) demonstrate that our approach outperforms existing state-of-the-art (SOTA) methods, achieving an average 9.40\% improvement of AUPRC and 12.35\% of AUROC in identifying semantic inconsistencies.
It excels at detecting fine-grained semantic errors, provides large language models with more granular feedback, and ultimately enhances the reliability and interpretability of data querying platforms. Our code is anonymously available at https://anonymous.4open.science/r/HeroSQL.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 2861