SNAILS: Schema Naming Assessments for Improved LLM-Based SQL Inference
Summary: Proposes schema naturalness as a data-centric lever to improve NL-to-SQL with LLMs. Introduces SNAILS: real-world schemas, labeled NL-SQL pairs, an identifier naturalness metric with automated modifiers, and cross-LLM evidence plus natural-views for NL-to-SQL workflows. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Kyle Luoma (United States Military Academy; University of California San Diego)
- 2. Arun Kumar (University of California San Diego)
BibTeX Citation
@inproceedings{luoma_sigmod25,
title = {{SNAILS: Schema Naming Assessments for Improved LLM-Based SQL Inference}},
author = {Luoma, Kyle and Kumar, Arun},
series = {{SIGMOD} '25},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3709727},
url = {https://dl.acm.org/doi/10.1145/3709727},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 6 of 6 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,444 | DBugScribe: Automatic Database Bug Reproduction from Community Reports | 2026 | SIGMOD | 4.9769913e-05 |
| 10,509 | ScaleDoc: Scaling LLM-based Predicates over Large Document Collections | 2026 | SIGMOD | 4.9769913e-05 |
| 10,643 | DIVER: A Robust Text-to-SQL System with Dynamic Interactive Value Linking and Evidence Reasoning | 2026 | SIGMOD | 4.9769913e-05 |
| 10,729 | TACO: A Benchmark for Open-Domain Text-to-SQL with Ambiguous and Cross-Database Queries | 2026 | VLDB | 4.9769913e-05 |
| 10,776 | A Comparative Evaluation of Schema Subsetting for LLM-based NL-to-SQL over Large-Schema Databases | 2026 | VLDB | 4.9769913e-05 |
| 10,949 | Bridging NL2SQL for CAN Signal Analytics at NIO: From Externalized Schemas to CTE Pipelines | 2026 | VLDB | 4.9769913e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 5 of 5 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 174 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB | 0.00026787121 |
| 533 | CodeS: Towards Building Open-source Language Models for Text-to-SQL | 2024 | SIGMOD | 0.00016818605 |
| 2,117 | NL2SQL is a solved problem... Not! | 2024 | CIDR | 9.011308e-05 |
| 3,353 | MT-Teql: Evaluating and Augmenting Neural NLIDB on Real-world Linguistic and Schema Variations | 2022 | VLDB | 7.3866512e-05 |
| 5,393 | SchemaPile: A Large Collection of Relational Database Schemas | 2024 | SIGMOD | 6.1494131e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,697 | SchemaRAG: A Schema-aware Retrieval-Augmented Generation Framework for Text-to-SQL | 2026 | SIGMOD |
| 2 | 11,336 | Evoschema: Towards Text-To-Sql Robustness Against Schema Evolution | 2025 | VLDB |
| 3 | 2,349 | The Dawn of Natural Language to SQL: Are We Fully Ready? | 2024 | VLDB |
| 4 | 7,013 | Reliable Text-to-SQL with Adaptive Abstention | 2025 | SIGMOD |
| 5 | 9,220 | Natural Language to SQL: State of the Art and Open Problems | 2025 | VLDB |
| 6 | 2,117 | NL2SQL is a solved problem... Not! | 2024 | CIDR |
| 7 | 174 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB |
| 8 | 3,489 | Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL | 2024 | VLDB |
| 9 | 10,705 | NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions | 2026 | VLDB |
| 10 | 10,776 | A Comparative Evaluation of Schema Subsetting for LLM-based NL-to-SQL over Large-Schema Databases | 2026 | VLDB |