Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.10318 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917205524873216 |
|---|---|
| author | Tian, Songsong Zhuo, Kongsheng Wang, Zhendong Shen, Rong Zhang, Shengtao Wu, Yong |
| author_facet | Tian, Songsong Zhuo, Kongsheng Wang, Zhendong Shen, Rong Zhang, Shengtao Wu, Yong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_10318 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Boundary-Aware NL2SQL: Integrating Reliability through Hybrid Reward and Data Synthesis Tian, Songsong Zhuo, Kongsheng Wang, Zhendong Shen, Rong Zhang, Shengtao Wu, Yong Computation and Language 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. |
| title | Boundary-Aware NL2SQL: Integrating Reliability through Hybrid Reward and Data Synthesis |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2601.10318 |