Cracking SQL Barriers: An LLM-based Dialect Translation System

Summary: CrackSQL leverages LLMs to translate SQL dialects via function-based segmentation, normalization, and translation-irrelevant abstraction for long, multi-syntax queries. A Cross-Dialect Syntax Embedding Model with a Local-to-Global loop enables targeted fixes and iterative translation. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: h839d949c59d37d41
Venue: SIGMOD
Year: 2025
Pagerank: 6.846192e-05
Overall Rank: 4,004 | 73.17%
DOI: 10.1145/3725278
PDF: Download (CC BY-ND 4.0)

Incoming Non-self Citations Over Time

Authors

1. Wei Zhou (Shanghai Jiao Tong University)
2. Yuyang Gao (Tsinghua University)
3. Xuanhe Zhou (Shanghai Jiao Tong University)
4. Guoliang Li (Tsinghua University)

BibTeX Citation

@inproceedings{zhou_sigmod25,
        title = {{Cracking SQL Barriers: An LLM-based Dialect Translation System}},
        author = {Zhou, Wei and Gao, Yuyang and Zhou, Xuanhe and Li, Guoliang},
        series = {{SIGMOD} '25},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3725278},
        url = {https://dl.acm.org/doi/10.1145/3725278},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 12 of 12 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
4,383	R-Bot: An LLM-based Query Rewrite System	2025	VLDB	6.6140223e-05
6,352	VikingMem: A Memory Base Management System for Stateful LLM-based Applications	2026	VLDB	5.78729e-05
10,382	Automated Database Testing via LLM-Synthesized SQL Features	2027	SIGMOD	4.9605343e-05
10,494	Automating Database-Native Function Code Synthesis with LLMs	2026	SIGMOD	4.9605343e-05
10,510	DBugScribe: Automatic Database Bug Reproduction from Community Reports	2026	SIGMOD	4.9605343e-05
10,514	Dialect-Agnostic SQL Parsing via LLM-Based Segmentation	2026	SIGMOD	4.9605343e-05
10,543	HAMMER: An Automatic RAG Tuning System via Hierarchical Memory-Guided Monte Carlo Tree Search	2026	SIGMOD	4.9605343e-05
10,787	DBAIOps: A Reasoning LLM-Enhanced Database Operation and Maintenance System using Knowledge Graphs	2026	VLDB	4.9605343e-05
10,962	Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System	2026	VLDB	4.9605343e-05
11,010	Bridging NL2SQL for CAN Signal Analytics at NIO: From Externalized Schemas to CTE Pipelines	2026	VLDB	4.9605343e-05
11,091	DialectEvo: Bridging SQL Dialects with Execution-Guided Knowledge Refinement	2026	VLDB	4.9605343e-05
13,653	DBCooker: A Database Kernel-Specialized Coding Agent Harness	2026	VLDB	-

Outgoing Citations (Sorted by Pagerank)

Showing 17 of 17 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
109	Extensible/Rule Based Query Rewrite Optimization in Starburst	1992	SIGMOD	0.00032702871
197	Grammar-like Functional Rules for Representing Query Optimization Alternatives	1988	SIGMOD	0.00025558952
236	OLTP-Bench: An Extensible Testbed for Benchmarking Relational Databases	2014	VLDB	0.00023639649
382	Apache Calcite: A Foundational Framework for Optimized Query Processing Over Heterogeneous Data Sources	2018	SIGMOD	0.0001946654
755	Natural language to SQL: Where are we today?	2020	VLDB	0.00014210408
1,032	Cost-Based Optimization for Magic: Algebra and Implementation	1996	SIGMOD	0.00012376627
1,656	D-Bot: Database Diagnosis System using Large Language Models	2024	VLDB	9.948529e-05
1,888	WeTune: Automatic Discovery and Verification of Query Rewrite Rules	2022	SIGMOD	9.4148912e-05
1,956	LLM-R^2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency	2025	VLDB	9.2927535e-05
2,117	The Dawn of Natural Language to SQL: Are We Fully Ready?	2024	VLDB	9.0012524e-05
2,227	GPTuner: A Manual-Reading Database Tuning System via GPT-Guided Bayesian Optimization	2024	VLDB	8.7924681e-05
2,389	A Learned Query Rewrite System using Monte Carlo Tree Search	2022	VLDB	8.5228689e-05
2,995	Panda: Performance Debugging for Databases using LLM Agents	2024	CIDR	7.7556154e-05
3,158	GenRewrite: Query Rewriting via Large Language Models	2026	SIGMOD	7.5676704e-05
4,729	LLM for Data Management	2024	VLDB	6.4317927e-05
5,521	Runtime-Extensible Parsers	2025	CIDR	6.0819893e-05
6,121	Breaking It Down: An In-depth Study of Index Advisors	2024	VLDB	5.863893e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	6,528	Reliable Text-to-SQL with Adaptive Abstention	2025	SIGMOD
2	755	Natural language to SQL: Where are we today?	2020	VLDB
3	9,242	Natural Language to SQL: State of the Art and Open Problems	2025	VLDB
4	7,972	The Power of Constraints in Natural Language to SQL Translation	2025	VLDB
5	163	Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation	2024	VLDB
6	4,917	Automated Validating and Fixing of Text-to-SQL Translation with Execution Consistency	2025	SIGMOD
7	10,514	Dialect-Agnostic SQL Parsing via LLM-Based Segmentation	2026	SIGMOD
8	11,448	Horizon: Robust Checks for SQL Migration Using LLMs	2025	VLDB
9	10,962	Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System	2026	VLDB
10	11,091	DialectEvo: Bridging SQL Dialects with Execution-Guided Knowledge Refinement	2026	VLDB