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

arXiv: https://arxiv.org/abs/2601.10318 · HTML: https://mlsanity.com/paper/2601.10318/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Synthetic reasoning data and bootstrapping, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 15 Jan 2026.

## Placed in

- Synthetic data and self-improvement for LLMs / [Synthetic reasoning data and bootstrapping](https://mlsanity.com/synth/synthetic-reasoning-data-and-bootstrapping/)

## Builds on (most cited first, 24 of 24)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [LEVER: Learning to Verify Language-to-Code Generation with Execution](https://mlsanity.com/paper/2302.08468/) (2023)
- [Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows](https://mlsanity.com/paper/2411.07763/) (2024)
- [GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing](https://mlsanity.com/paper/2009.13845/) (2020)
- [DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning](https://mlsanity.com/paper/2511.22570/) (2025)
- [A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization](https://mlsanity.com/paper/1902.01069/) (2019)
- [Grounded Adaptation for Zero-shot Executable Semantic Parsing](https://mlsanity.com/paper/2009.07396/) (2020)
- [SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning](https://mlsanity.com/paper/2504.08600/) (2025)
- [Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing](https://mlsanity.com/paper/1807.02322/) (2018)
- [Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness](https://mlsanity.com/paper/2301.08881/) (2023)
- [OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment](https://mlsanity.com/paper/2502.14913/) (2025)
- [RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thought](https://mlsanity.com/paper/2305.11499/) (2023)
- [SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL](https://mlsanity.com/paper/2111.00653/) (2021)
- [Importance of Synthesizing High-quality Data for Text-to-SQL Parsing](https://mlsanity.com/paper/2212.08785/) (2022)
- [ExCoT: Optimizing Reasoning for Text-to-SQL with Execution Feedback](https://mlsanity.com/paper/2503.19988/) (2025)
- [Reliable Text-to-SQL with Adaptive Abstention](https://mlsanity.com/paper/2501.10858/) (2025)
- [PRACTIQ: A Practical Conversational Text-to-SQL dataset with Ambiguous and Unanswerable Queries](https://mlsanity.com/paper/2410.11076/) (2024)
- [You Only Read Once (YORO): Learning to Internalize Database Knowledge for Text-to-SQL](https://mlsanity.com/paper/2409.12172/) (2024)
- [AmbiSQL: Interactive Ambiguity Detection and Resolution for Text-to-SQL](https://mlsanity.com/paper/2508.15276/) (2025)
- [RetrySQL: text-to-SQL training with retry data for self-correcting query generation](https://mlsanity.com/paper/2507.02529/) (2025)
- [HES-SQL: Hybrid Reasoning for Efficient Text-to-SQL with Structural Skeleton Guidance](https://mlsanity.com/paper/2510.08896/) (2025)

## Abstract (arXiv)

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.