arXiv Machine Learning September 22, 2026 By Xiang Zhang, Hongming Xu, Le Zhou, Wei Zhou, Xuanhe Zhou, Guoliang Li, Yuyu Luo, Changdong Liu, Guorun Chen, Jiang Liao, Fan Wu

Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System

Read the original on arXiv Machine Learning →

The paper introduces Dial, a knowledge‑grounded framework for generating SQL queries that respect the specific dialect of heterogeneous database systems. Dial comprises a Dialect‑Aware Logical Query Planning module, a hierarchical intent‑aware knowledge base (HINT‑KB) containing canonical syntax, function, and constraint repositories, and an execution‑driven debugging loop that separates syntactic recovery from logic auditing. The authors also present DS‑NL2SQL, a benchmark of 2,218 dialect‑specific test cases across six major database systems, and report that Dial improves translation accuracy by 10.25% and dialect feature coverage by 15.77% over existing baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 9

UniQL: Towards Dialect-Universal Benchmarking for Text-to-SQL

arXiv:2606. 08018v1 Announce Type: new Abstract: Existing text-to-SQL benchmarks are largely centered on SQLite, making it difficult to evaluate whether models can generalize across heterogeneous SQL dialects.

By Jianling Gao, Chongyang Tao, Jiayuan Bai, Liu Yang, Xuanguang Pan, Jinrui Liu, Shihao Xing, Xiaohan Xu, Jie Liang, Shuai Ma

llms nlp benchmarks data-engineering

arXiv AI

Sep 10

ProcArena: A Multi-Scenario Benchmark for LLMs on Direct and Interactive PL/SQL Development from Natural Language

ProcArena is a new benchmark for evaluating large language models on natural‑language to PL/SQL translation tasks. It contains 3,998 executable tasks across 157 databases, covering nine development subscenarios in PostgreSQL and Oracle, and supports both direct generation and interactive multi‑turn scenarios. Experiments on seven models show that even the best performers achieve only about 62% accuracy in direct mode and 58% in interactive mode, highlighting the difficulty of realistic NL‑to‑PL/SQL development.

By Hang Zhang, Chaokun Wang, Yuzhi Pan, Ziyao Zhong, Shuo Cao, Yue Xue, Zeyu Huang, Xingwei Zhou, Fang Niu, Bofan Xie, Guanchen Ge, Leqi Zheng, Ziyang Liu, Xiannian Cao, Pengcheng Ge

llms benchmarks data-engineering

arXiv AI

Sep 10

SQLMorph: Query Mutation and Fine-Grained Metrics for Text-to-SQL Evaluation

arXiv:2609.08950v1 Announce Type: cross Abstract: Text-to-SQL systems translate natural language queries into executable SQL, democratizing access to structured data. Despite recent advances driven b...

By Mohammadhossein Malekpour, Mohamed Riahi, Maxime Lamothe, Amine Mhedhbi

llms benchmarks data-engineering

arXiv AI

2d ago

The Stochastic Shift: A New Evaluation Paradigm for Text-to-SQL with AI Operators

arXiv:2609.21133v1 Announce Type: cross Abstract: SQL has been augmented with AI operators, enabling modern data analytics platforms to derive insights from both structured and unstructured data. We...

By Tarfah Alrashed, Fatma Ozcan, Per Jacobsson, Tal Neiman, Xianshun Chen

llms benchmarks data-engineering

arXiv AI

Jun 16

Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuning

arXiv:2606. 15598v1 Announce Type: new Abstract: Text-to-SQL aims to translate natural language questions into executable SQL queries over structured databases, enabling non-expert users to access data intuitively.

By Feng Lyu, Jinfeng Cen, Sijing Duan, Hao Wu, Shucheng Li, Weixu Zhang, Haolun Wu

llms fine-tuning benchmarks data-engineering

arXiv AI

Sep 1

BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotations

arXiv:2608.29345v1 Announce Type: new Abstract: While recent Large Language Model (LLM)-based text-to-SQL systems achieve impressive performance on standard benchmarks, they struggle when user querie...

By Yunfan Zhou, Qiming Shi, Yizhou Yang, Di Weng, Yingcai Wu

llms benchmarks data-engineering

One email a morning, machine-written

Related stories

UniQL: Towards Dialect-Universal Benchmarking for Text-to-SQL

ProcArena: A Multi-Scenario Benchmark for LLMs on Direct and Interactive PL/SQL Development from Natural Language

SQLMorph: Query Mutation and Fine-Grained Metrics for Text-to-SQL Evaluation

The Stochastic Shift: A New Evaluation Paradigm for Text-to-SQL with AI Operators

Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuning

BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotations