Boundary-Aware NL2SQL: Integrating Reliability through Hybrid Reward and Data Synthesis

TL;DR

BAR-SQL is a novel NL2SQL framework that enhances reliability and boundary-awareness through data synthesis, interpretability techniques, and a hybrid reward training process, achieving high accuracy and abstention performance.

Contribution

It introduces a boundary-aware training framework with data synthesis, interpretability, and a hybrid reward mechanism, advancing the reliability of NL2SQL models.

Findings

Achieves 91.48% SQL accuracy on Ent-SQL-Bench

Outperforms proprietary models like Claude 4.5 Sonnet and GPT-5

Demonstrates effective boundary-aware abstention in ambiguous queries

Abstract

In this paper, we present BAR-SQL (Boundary-Aware Reliable NL2SQL), a unified training framework that embeds reliability and boundary awareness directly into the generation process. We introduce a Seed Mutation data synthesis paradigm that constructs a representative enterprise corpus, explicitly encompassing multi-step analytical queries alongside boundary cases including ambiguity and schema limitations. To ensure interpretability, we employ Knowledge-Grounded Reasoning Synthesis, which produces Chain-of-Thought traces explicitly anchored in schema metadata and business rules. The model is trained through a two-stage process: Supervised Fine-Tuning (SFT) followed by Reinforcement Learning via Group Relative Policy Optimization. We design a Task-Conditioned Hybrid Reward mechanism that simultaneously optimizes SQL execution accuracy-leveraging Abstract Syntax Tree analysis and dense result matching-and semantic precision in abstention responses. To evaluate reliability alongside generation accuracy, we construct and release Ent-SQL-Bench, which jointly assesse SQL precision and boundary-aware abstention across ambiguous and unanswerable queries. Experimental results on this benchmark demonstrate that BAR-SQL achieves 91.48% average accuracy, outperforming leading proprietary models, including Claude 4.5 Sonnet and GPT-5, in both SQL generation quality and boundary-aware abstention capability. The source code and benchmark are available anonymously at: https://github.com/TianSongS/BAR-SQL.