Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System

Xiang Zhang; Hongming Xu; Le Zhou; Wei Zhou; Xuanhe Zhou; Guoliang Li; Yuyu Luo; Changdong Liu

cs.DBMar 8, 2026

Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System

Authors: Xiang Zhang, Hongming Xu, Le Zhou, Wei Zhou, Xuanhe Zhou, Guoliang Li, Yuyu Luo, Changdong Liu,

Organizations: Shanghai Jiao Tong Univ. · Tsinghua University · HKUST (GZ) · Shanghai Ideal Information Industry (Group) ·

Abstract

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 canonical 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.

Figures & tables

Figure 1. Dialect-Specific NL2SQL Failures.

Figure 3. Dialect-Specific Error Analysis.

Operator	Semantic Definition	Description Example
Data Sourcing ( $\mathcal{O}_{src}$ )	Specifies base relations and logical associations, including ANSI joins and dialect-specific correlations such as LATERAL or APPLY .	Source Match and League where Match.league_id = League.id .
Filtering ( $\mathcal{O}_{flt}$ )	Selects tuples using row-level or post-aggregation predicates.	Keep orders after 2020-01-01 and with status = ’completed’
Scalar Calculation ( $\mathcal{O}_{cal}$ )	Computes derived values through row-level transformations, such as casting, string operations, and temporal arithmetic.	Compute amount * 1.08 as amount_with_tax .
Aggregation ( $\mathcal{O}_{agg}$ )	Changes data granularity by grouping records and computing summary metrics.	Group by customer_id and compute AVG(amount) .
Result Organization ( $\mathcal{O}_{org}$ )	Organizes final results through projection, ordering, and cardinality control.	Sort by avg_amount descending and keep top 10.
Auxiliary Operation ( $\mathcal{O}_{aux}$ )	Captures query-structuring requirements that organize, scope, or combine intermediate logical results, such as CTEs, nested queries, set operations, and window structures.	Use CTEs to compare department and company averages.

Table 1. Standardized Logical Operators in NL-LQP.

Figure 4. Dialect-Aware Logical Query Planning.

Benchmark	Dialect-Specific NL2SQL	Multi-Dialect NL-SQL	Dialectal Incompatibility	Execution Equivalence	# Test Samples	# Dialect Types	# Test Databases	Average Dialectal Discrepancy
Spider ( Yu et al., 2018 )	✗	✗	✗	✗	2,147	1	206	–
BIRD ( Li et al., 2023 )	✗	✗	✗	✗	1,789	1	15	–
BIRD Mini-Dev ( Li et al., 2023 )	✓	✓	✓	✗	500	3	11	1.60
PARROT ( Zhou et al., 2025b )	✗	✗	✓	✓	598	8	–	–
Spider 2.0-Lite ( Lei et al., 2025 )	✓	✗	✗	✗	547	3	158	–
DS-NL2SQL	✓	✓	✓	✓	2,218	6	796	3.67

Table 2. Comparison of our Dialect-Specific NL2SQL Benchmark with other representative benchmarks.

Method	SQLite			PostgreSQL			MySQL			SQL Server			DuckDB			Oracle
Method	Exec	Acc	DFC	Exec	Acc	DFC	Exec	Acc	DFC	Exec	Acc	DFC	Exec	Acc	DFC	Exec	Acc	DFC
Input Prompting
DIN-SQL	83.36	44.27	63.75	69.07	37.83	40.94	49.95	29.13	33.59	73.67	40.08	48.05	65.28	36.93	42.72	66.73	39.13	53.16
Agentar-Scale-SQL	98.69	50.36	74.93	82.10	41.25	44.63	77.95	37.96	48.87	65.24	31.70	37.82	85.75	44.23	54.43	78.58	42.25	50.16
Agentar-Scale-SQL (top-8 upper bound)	99.86	61.90	82.94	91.84	50.45	54.33	86.56	46.26	56.88	74.89	41.07	48.39	94.77	48.30	63.30	92.70	48.76	68.60
Model Finetuning

Table 3. Main performance comparison on DS-NL2SQL across six database dialects. Exec : Executability (%), Acc : Execution Accuracy (%), DFC : Dialect Feature Coverage (%).

Figure 5. Overall Performance Comparison.

Method	Logic Query Planning	HINT-KB	Correction	PostgreSQL			SQL Server			Oracle
Method	Logic Query Planning	HINT-KB	Correction	Exec	Acc	DFC	Exec	Acc	DFC	Exec	Acc	DFC
Dial	✓	✓	✓	98.33	53.33	78.70	99.00	51.71	85.70	99.21	53.42	76.97
Ablation Variants	1-step NL-LQP	✓	✓	95.52	49.04	68.15	91.48	47.09	69.49	93.72	50.73	66.51
	✗	✓	✓	91.64	38.59	53.35	98.16	48.35	69.13	95.16	43.99	52.41
	✓	✓	✗	96.98	43.17	58.70	93.21	44.49	61.90	98.35	43.76	51.97
	✓	✗	✗	96.53	45.94	61.92	95.63	46.71	61.26	91.34	43.15	48.52

Table 4. Performance Comparison of Dial Variants.

Type	User Question (Abbreviated Intent)	Target Syntax Constraints (Gold)	DIN-SQL	EXESQL	Dialect-SQL	Agentar+SQLGlot	Dial	Target Dialect
U1	List all IP addresses accessed by each city.	LISTAGG(…) (Strictly NO GROUP_CONCAT )	$\times$	$\times$	$\times$	$\times$	✓	Oracle
U2	Find the shipment details matching the ID.	CAST(id AS CHAR) (Strictly NO AS TEXT )	$\times$	✓	✓	$\times$	✓	MySQL
U3	When did the earliest complaint start on 2017-03-22?	TO_DATE(…) (Strictly NO date() function)	$\times$	$\times$	$\times$	$\times$	✓	Oracle
U4	What are the total sales metrics for last month?	Native Numeric (Strictly NO ORM bindings )	✓	✓	$\times$	✓	✓	DuckDB
M1	Combine first, middle, and last names.	first \|\| middle \|\| last (Strictly NO 3-arg CONCAT )	$\times$	$\times$	$\times$	✓	✓	Oracle
M2	Retrieve user details across multiple related logs.	FROM "T1" "T2" (Strictly NO AS keyword)	✓	$\times$	✓	✓	✓	Oracle

Table 5. Dialect-Specific Generation Errors Effectively Resolved by Dial (User questions are abstracted as realistic questions. Target syntax highlights the correct dialect-specific pattern alongside strictly prohibited anti-patterns).

Method	PostgreSQL			SQL Server			Oracle
Method	Exec	Acc	DFC	Exec	Acc	DFC	Exec	Acc	DFC
Dial (Ours)
Qwen-3-Max	98.33	53.33	78.70	99.00	51.71	85.70	99.21	53.42	76.97
DeepSeek-V3.2	96.42	43.10	63.10	99.42	45.39	65.27	98.03	45.77	60.08
GPT-5.2	96.88	48.91	70.95	99.76	51.68	76.84	99.70	48.89	66.64
DIN-SQL

Table 6. Performance over Different LLM Backbones.

Execution-Guided Text-to-SQL

See all 17 papers

UniQL: Towards Dialect-Universal Benchmarking for Text-to-SQL
Jun 6, 2026Jianling Gao, Chongyang Tao, Jiayuan Bai +7LLM Evaluation Text-to-SQL
1SKLCCSE, Beihang University · 2The University of Hong Kong
Closing the Cross-Dialect Gap: Query Plans as a Portable Interface in Text-to-SQL
Sep 27, 2026Corentin Royer, Robin Oester, Yotam Perlitz +3Text-to-SQL Relational Databases
IBM Research, Zurich, Switzerland · ETH Zurich, Zurich, Switzerland
PolySQL: Scaling Text-to-SQL Evaluation Across SQL Dialects via Automated Backend Isomorphism
May 8, 2026Yotam Perlitz, Elad Venezian, Corentin Royer +2Benchmark Design Text-to-SQL
1IBM Research AI · 2ETH Zürich

Jun 6, 2026J/K move · Enter open · S save

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

Jianling Gao, Chongyang Tao, Jiayuan Bai, Liu Yang+6

1SKLCCSE, Beihang University · 2The University of Hong Kong

LLM Evaluation Text-to-SQL Relational Databases Text-to-SQL Evaluation

Open paper AskPDF arXiv

Existing text-to-SQL benchmarks are largely centered on SQLite, making it difficult to evaluate whether models can generalize across heterogeneous SQL dialects. However, real-world database systems differ substantially in syntax, functions, type systems, and execution semantics, so the same natural language intent often requires dialect-specific SQL realizations. We introduce UniQL, a human-verified benchmark for cross-dialect text-to-SQL evaluation. UniQL aligns 1,534 natural language questions with executable SQL annotations across 16 SQL dialects, yielding 24,544 dialect-specific queries. All dialects share the same intents, aligned schemas and database contents, enabling controlled evaluation of dialect generalization. UniQL is constructed through a hybrid pipeline combining database migration, SQL translation, execution-guided verification, iterative rule summarization, and human validation. Experiments on both open-source and closed-source LLMs show that current models remain far from dialect-universal, with substantial performance variation across database systems and limited transfer from SQLite success to other dialects. These findings highlight the need for aligned cross-dialect benchmarks and more dialect-aware text-to-SQL methods. Code and data are available at https://github.com/JerryGao818/UniQL

Abstract

Execution-Guided Text-to-SQL

Explore similar work

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

Closing the Cross-Dialect Gap: Query Plans as a Portable Interface in Text-to-SQL

PolySQL: Scaling Text-to-SQL Evaluation Across SQL Dialects via Automated Backend Isomorphism