DBScholar

Back to papers

Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL

Summary: ZeroNL2SQL: fine-tuned SLMs (with novel database serialization and question-aware schema alignment) generate SQL sketches, then LLMs fill missing clauses and values. Multi-level value matching plus execution-based selection yields SOTA zero-shot NL2SQL (+5.5–20% execution accuracy). (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
h838501df0892a9cc
Venue
VLDB
Year
2024
Pagerank
7.3650961e-05
Overall Rank
3,358 | 77.50%
DOI
10.14778/3681954.3681960
PDF
Download (CC BY-NC-ND 4.0)

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{fan_vldb24,
        title = {{Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL}},
        author = {Fan, Ju and Gu, Zihui and Zhang, Songyue and Zhang, Yuxin and Chen, Zui and Cao, Lei and Li, Guoliang and Madden, Samuel and Du, Xiaoyong and Tang, Nan},
        journal = {PVLDB},
        series = {{VLDB} '24},
        volume = {17},
        number = {11},
        pages = {2753--2763},
        doi = {10.14778/3681954.3681960},
        url = {https://doi.org/10.14778/3681954.3681960},
        year = {2024}
}

Incoming Citations (Sorted by Pagerank)

Showing 22 of 22 citing papers.

Rank Citing Paper Year Venue Pagerank
3,286 In-depth Analysis of Graph-based RAG in a Unified Framework 2025 VLDB 7.441688e-05
4,383 R-Bot: An LLM-based Query Rewrite System 2025 VLDB 6.6140223e-05
8,320 ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries 2025 VLDB 5.3404439e-05
9,946 AgentTune: An Agent-Based Large Language Model Framework for Database Knob Tuning 2026 SIGMOD 5.0910746e-05
10,323 This is Going to Sound Crazy, But What If We Used Large Language Models to Boost Automatic Database Tuning Algorithms By Leveraging Prior History? We Will Find Better Configurations More Quickly Than Retraining From Scratch! 2026 SIGMOD 5.0241309e-05
10,383 Benchmarking Text-to-SQL under Role-Based Access Control 2027 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
10,565 OctoSelector: Efficient and Effective Batch-Aware Model Selection for Large Language Models 2026 SIGMOD 4.9605343e-05
10,574 Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards 2026 SIGMOD 4.9605343e-05
10,593 VecBench: A Controllable Benchmark for Filtered Vector Search: [Experiments & Analysis] 2026 SIGMOD 4.9605343e-05
10,621 Are Your LLM-based Text-to-SQL Models Secure? Exploring SQL Injection via Backdoor Attacks 2026 SIGMOD 4.9605343e-05
10,646 GeoKGM: A Multimodal Large Language Model for Zero-Shot Knowledge Graph Completion in Geospatial Databases 2026 SIGMOD 4.9605343e-05
10,658 PLForge: Enhancing Language Models for Natural Language to Procedural Extensions of SQL 2026 SIGMOD 4.9605343e-05
10,667 Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding 2026 SIGMOD 4.9605343e-05
10,762 The Case For Language Model Approximated LIKE Predicate 2026 SIGMOD 4.9605343e-05
10,766 NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions 2026 VLDB 4.9605343e-05
10,790 TACO: A Benchmark for Open-Domain Text-to-SQL with Ambiguous and Cross-Database Queries 2026 VLDB 4.9605343e-05
10,809 OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision 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
11,099 Graph-Based Retrieval-Augmented Generation: Applications, Challenges, Solutions, and Opportunities 2026 VLDB 4.9605343e-05
11,334 Weak-to-Strong Prompts with Lightweight-to-Powerful LLMs for High-Accuracy, Low-Cost, and Explainable Data Transformation 2025 VLDB 4.9605343e-05
11,438 Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models 2025 VLDB 4.9605343e-05
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 7 of 7 cited papers.

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

Rank Cited Paper Year Venue Pagerank
163 Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation 2024 VLDB 0.00027456647
501 CodeS: Towards Building Open-source Language Models for Text-to-SQL 2024 SIGMOD 0.00017239952
1,358 Symphony: Towards Natural Language Query Answering over Multi-modal Data Lakes 2023 CIDR 0.00010902306
2,216 Few-shot Text-to-SQL Translation using Structure and Content Prompt Learning 2023 SIGMOD 8.8249841e-05
3,166 Unicorn: A Unified Multi-tasking Model for Supporting Matching Tasks in Data Integration 2023 SIGMOD 7.5597853e-05
5,830 Domain Adaptation for Deep Entity Resolution 2022 SIGMOD 5.9627079e-05
11,904 OpenTFV: An Open Domain Table-Based Fact Verification System 2022 SIGMOD 4.9605343e-05
Previous Page 1 / 1 Next

Semantically Similar Papers

# Overall Rank Paper Year Venue
1 163 Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation 2024 VLDB
2 755 Natural language to SQL: Where are we today? 2020 VLDB
3 6,528 Reliable Text-to-SQL with Adaptive Abstention 2025 SIGMOD
4 1,209 CatSQL: Towards Real World Natural Language to SQL Applications 2023 VLDB
5 7,972 The Power of Constraints in Natural Language to SQL Translation 2025 VLDB
6 2,117 The Dawn of Natural Language to SQL: Are We Fully Ready? 2024 VLDB
7 2,118 NL2SQL is a solved problem... Not! 2024 CIDR
8 10,837 A Comparative Evaluation of Schema Subsetting for LLM-based NL-to-SQL over Large-Schema Databases 2026 VLDB
9 9,242 Natural Language to SQL: State of the Art and Open Problems 2025 VLDB
10 10,766 NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions 2026 VLDB