Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914378536714240 |
|---|---|
| author | Zhang, Xiang Xu, Hongming Zhou, Le Zhou, Wei Zhou, Xuanhe Li, Guoliang Luo, Yuyu Liu, Changdong Chen, Guorun Liao, Jiang Wu, Fan |
| author_facet | Zhang, Xiang Xu, Hongming Zhou, Le Zhou, Wei Zhou, Xuanhe Li, Guoliang Luo, Yuyu Liu, Changdong Chen, Guorun Liao, Jiang Wu, Fan |
| contents | Enterprises commonly deploy heterogeneous database systems, each of which owns a distinct SQL dialect with different syntax rules, built-in functions, and execution constraints. However, most existing NL2SQL methods assume a single dialect (e.g., SQLite) and struggle to produce queries that are both semantically correct and executable on target engines. Prompt-based approaches tightly couple intent reasoning with dialect syntax, rule-based translators often degrade native operators into generic constructs, and multi-dialect fine-tuning suffers from cross-dialect interference.
In this paper, we present Dial, a knowledge-grounded framework for dialect-specific NL2SQL. Dial introduces: (1) a Dialect-Aware Logical Query Planning module that converts natural language into a dialect-aware logical query plan via operator-level intent decomposition and divergence-aware specification; (2) HINT-KB, a hierarchical intent-aware knowledge base that organizes dialect knowledge into (i) a canonical syntax reference, (ii) a declarative function repository, and (iii) a procedural constraint repository; and (3) an execution-driven debugging and semantic verification loop that separates syntactic recovery from logic auditing to prevent semantic drift. We construct DS-NL2SQL, a benchmark covering six major database systems with 2,218 dialect-specific test cases. Experimental results show that Dial consistently improves translation accuracy by 10.25% and dialect feature coverage by 15.77% over state-of-the-art baselines. The code is at https://github.com/weAIDB/Dial. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07449 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System Zhang, Xiang Xu, Hongming Zhou, Le Zhou, Wei Zhou, Xuanhe Li, Guoliang Luo, Yuyu Liu, Changdong Chen, Guorun Liao, Jiang Wu, Fan Databases Artificial Intelligence Computation and Language Information Retrieval Machine Learning Enterprises commonly deploy heterogeneous database systems, each of which owns a distinct SQL dialect with different syntax rules, built-in functions, and execution constraints. However, most existing NL2SQL methods assume a single dialect (e.g., SQLite) and struggle to produce queries that are both semantically correct and executable on target engines. Prompt-based approaches tightly couple intent reasoning with dialect syntax, rule-based translators often degrade native operators into generic constructs, and multi-dialect fine-tuning suffers from cross-dialect interference. In this paper, we present Dial, a knowledge-grounded framework for dialect-specific NL2SQL. Dial introduces: (1) a Dialect-Aware Logical Query Planning module that converts natural language into a dialect-aware logical query plan via operator-level intent decomposition and divergence-aware specification; (2) HINT-KB, a hierarchical intent-aware knowledge base that organizes dialect knowledge into (i) a canonical syntax reference, (ii) a declarative function repository, and (iii) a procedural constraint repository; and (3) an execution-driven debugging and semantic verification loop that separates syntactic recovery from logic auditing to prevent semantic drift. We construct DS-NL2SQL, a benchmark covering six major database systems with 2,218 dialect-specific test cases. Experimental results show that Dial consistently improves translation accuracy by 10.25% and dialect feature coverage by 15.77% over state-of-the-art baselines. The code is at https://github.com/weAIDB/Dial. |
| title | Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System |
| topic | Databases Artificial Intelligence Computation and Language Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2603.07449 |