Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQL
Summary: Empirical study of long-context Gemini-1.5-Pro for NL2SQL, varying schemas, examples, demonstrations, hints, and documentation. Finds extended context improves robust generation without fine-tuning, while quantifying accuracy–latency tradeoffs across benchmarks. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Yeounoh Chung (Google)
- 2. Gaurav T. Kakkar (Google)
- 3. Yu Gan (Google)
- 4. Brenton Milne (Google)
- 5. Fatma Özcan (Google)
BibTeX Citation
@article{chung_vldb25,
title = {{Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQL}},
author = {Chung, Yeounoh and Kakkar, Gaurav T. and Gan, Yu and Milne, Brenton and Özcan, Fatma},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {8},
pages = {2735--2747},
doi = {10.14778/3742728.3742761},
url = {https://doi.org/10.14778/3742728.3742761},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 3 of 3 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 9,870 | Natural Language to SQL: State of the Art and Open Problems | 2025 | VLDB | 5.2043672e-05 |
| 10,217 | DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework | 2026 | SIGMOD | 5.093636e-05 |
| 10,483 | PRISM: Navigating Cost–Accuracy Trade-offs for NL2SQL | 2026 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
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 |
|---|---|---|---|---|
| 279 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB | 0.00022468369 |
| 2,602 | NL2SQL is a solved problem... Not! | 2024 | CIDR | 8.3535452e-05 |
| 2,852 | The Dawn of Natural Language to SQL: Are We Fully Ready? | 2024 | VLDB | 8.0455088e-05 |
| 6,870 | Natural Language Interfaces for Databases with Deep Learning | 2023 | VLDB | 5.7497843e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 6,936 | Reliable Text-to-SQL with Adaptive Abstention | 2025 | SIGMOD |
| 2 | 865 | Natural language to SQL: Where are we today? | 2020 | VLDB |
| 3 | 8,140 | Automated Data Visualization from Natural Language via Large Language Models: An Exploratory Study | 2024 | SIGMOD |
| 4 | 279 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB |
| 5 | 9,305 | The Power of Constraints in Natural Language to SQL Translation | 2025 | VLDB |
| 6 | 10,510 | NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions | 2026 | VLDB |
| 7 | 4,045 | Logical and Physical Optimizations for SQL Query Execution over Large Language Models | 2025 | SIGMOD |
| 8 | 3,787 | Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL | 2024 | VLDB |
| 9 | 2,602 | NL2SQL is a solved problem... Not! | 2024 | CIDR |
| 10 | 9,870 | Natural Language to SQL: State of the Art and Open Problems | 2025 | VLDB |