A Comparative Evaluation of Schema Subsetting for LLM-based NL-to-SQL over Large-Schema Databases
Summary: Evaluates seven schema-subsetting methods across Bird, Spider 2, SNAILS, and new BigBird, with task-specific accuracy/efficiency metrics. Finds subsetting often harms small-schema accuracy but can reduce tokens on large schemas; introduces hybrid SKALPEL. (summarized by gpt-5.6-luna on Aug 17 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Kyle Luoma (United States Military Academy)
- 2. Arun Kumar (University of California San Diego)
BibTeX Citation
@article{luoma_vldb26,
title = {{A Comparative Evaluation of Schema Subsetting for LLM-based NL-to-SQL over Large-Schema Databases}},
author = {Luoma, Kyle and Kumar, Arun},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {9},
pages = {2019--2031},
doi = {10.14778/3819518.3819531},
url = {https://doi.org/10.14778/3819518.3819531},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 3 of 3 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 533 | CodeS: Towards Building Open-source Language Models for Text-to-SQL | 2024 | SIGMOD | 0.00016826571 |
| 2,025 | OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment | 2025 | SIGMOD | 9.163622e-05 |
| 4,924 | SNAILS: Schema Naming Assessments for Improved LLM-Based SQL Inference | 2025 | SIGMOD | 6.3512934e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 8,016 | Generating Succinct Descriptions of Database Schemata for Cost-Efficient Prompting of Large Language Models | 2024 | VLDB |
| 2 | 10,893 | Developing and Benchmarking Verification Algorithms to Improve Text-to-SQL Generation | 2026 | VLDB |
| 3 | 7,952 | The Power of Constraints in Natural Language to SQL Translation | 2025 | VLDB |
| 4 | 2,117 | NL2SQL is a solved problem... Not! | 2024 | CIDR |
| 5 | 174 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB |
| 6 | 2,348 | The Dawn of Natural Language to SQL: Are We Fully Ready? | 2024 | VLDB |
| 7 | 7,012 | Reliable Text-to-SQL with Adaptive Abstention | 2025 | SIGMOD |
| 8 | 4,924 | SNAILS: Schema Naming Assessments for Improved LLM-Based SQL Inference | 2025 | SIGMOD |
| 9 | 3,489 | Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL | 2024 | VLDB |
| 10 | 10,695 | NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions | 2026 | VLDB |