OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment

Summary: OpenSearch-SQL proposes a modular Text-to-SQL pipeline with a Consistency Alignment module to curb instruction deviations and hallucinations. It uses a SQL-Like intermediate language and dynamic few-shot Query-CoT-SQL to run base LLMs without fine-tuning, achieving top EX and R-VES on BIRD. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 7250
Venue: SIGMOD
Year: 2025
Pagerank: 6.6907933e-05
Overall Rank: 3,859 | 73.16%
DOI: 10.1145/3725331

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 9 of 9 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
9,995	Text-to-SQL Benchmarks are Broken: An In-Depth Analysis of Annotation Errors	2026	CIDR	4.1945683e-05
10,051	Are Your LLM-based Text-to-SQL Models Secure? Exploring SQL Injection via Backdoor Attacks	2026	SIGMOD	4.1945683e-05
10,108	Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding	2026	SIGMOD	4.1945683e-05
10,115	ST-Raptor: LLM-Powered Semi-Structured Table Question Answering	2026	SIGMOD	4.1945683e-05
10,143	Beluga: A CXL-Based Memory Architecture for Scalable and Efficient LLM KVCache Management	2026	SIGMOD	4.1945683e-05
10,155	DIVER: A Robust Text-to-SQL System with Dynamic Interactive Value Linking and Evidence Reasoning	2026	SIGMOD	4.1945683e-05
10,221	NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions	2026	VLDB	4.1945683e-05
10,268	OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision	2026	VLDB	4.1945683e-05
10,327	Pervasive Annotation Errors Break Text-to-SQL Benchmarks and Leaderboards	2026	VLDB	4.1945683e-05

Outgoing Citations (Sorted by Pagerank)

Showing 4 of 4 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
54	DISCOVER: Keyword Search in Relational Databases	2002	VLDB	0.00066047203
276	Efficient IR-Style Keyword Search over Relational Databases	2003	VLDB	0.00029336949
369	Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation	2024	VLDB	0.0002547515
998	CodeS: Towards Building Open-source Language Models for Text-to-SQL	2024	SIGMOD	0.00014729379

Semantically Similar Papers

Overall Rank	Paper	Year	Venue	Pagerank
10,451	RTS+: Reliable Text to SQL	2025	SIGMOD	4.1945683e-05
3,978	OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale	2025	VLDB	6.5725884e-05
4,908	Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL	2024	VLDB	5.8339245e-05
5,840	Logical and Physical Optimizations for SQL Query Execution over Large Language Models	2025	SIGMOD	5.3042561e-05
998	CodeS: Towards Building Open-source Language Models for Text-to-SQL	2024	SIGMOD	0.00014729379
7,354	Reliable Text-to-SQL with Adaptive Abstention	2025	SIGMOD	4.7529612e-05
8,896	SQL-Factory: A Multi-Agent Framework for High-Quality and Large-Scale SQL Generation	2026	VLDB	4.427232e-05
369	Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation	2024	VLDB	0.0002547515
10,221	NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions	2026	VLDB	4.1945683e-05
10,268	OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision	2026	VLDB	4.1945683e-05