DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework
Summary: Recasts Text-to-SQL as a software-engineering workflow following SDLC, combining relationally closed schema linking, N-version generation, pre-execution Syntax-Logic-Quality checks, and confidence-aware adjudication. Achieves strong BIRD/Spider accuracy with a small, untuned MoE, emphasizing orchestration over scale. (summarized by gpt-5.6-luna on Jul 26 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Boyan Li (Hong Kong University of Science and Technology)
- 2. Chong Chen (Huawei)
- 3. Zhujun Xue (Huawei)
- 4. Yinan Mei (Huawei)
- 5. Yuyu Luo (Hong Kong University of Science and Technology)
BibTeX Citation
@inproceedings{li_sigmod26,
title = {{DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework}},
author = {Li, Boyan and Chen, Chong and Xue, Zhujun and Mei, Yinan and Luo, Yuyu},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3802035},
url = {https://dl.acm.org/doi/10.1145/3802035},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,556 | OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision | 2026 | VLDB | 5.093636e-05 |
| 10,587 | LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning | 2026 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 9 of 9 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 |
| 756 | CodeS: Towards Building Open-source Language Models for Text-to-SQL | 2024 | SIGMOD | 0.0001431656 |
| 2,395 | OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale | 2025 | VLDB | 8.6355093e-05 |
| 2,710 | OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment | 2025 | SIGMOD | 8.2206448e-05 |
| 4,809 | Synthesizing Natural Language to Visualization (NL2VIS) Benchmarks from NL2SQL Benchmarks | 2021 | SIGMOD | 6.4984309e-05 |
| 5,366 | HAIChart: Human and AI Paired Visualization System | 2024 | VLDB | 6.2457679e-05 |
| 7,332 | Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQL | 2025 | VLDB | 5.6433374e-05 |
| 9,870 | Natural Language to SQL: State of the Art and Open Problems | 2025 | VLDB | 5.2043672e-05 |
| 10,285 | Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards | 2026 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 756 | CodeS: Towards Building Open-source Language Models for Text-to-SQL | 2024 | SIGMOD |
| 2 | 10,398 | Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding | 2026 | SIGMOD |
| 3 | 10,444 | DIVER: A Robust Text-to-SQL System with Dynamic Interactive Value Linking and Evidence Reasoning | 2026 | SIGMOD |
| 4 | 2,710 | OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment | 2025 | SIGMOD |
| 5 | 6,267 | Automated Validating and Fixing of Text-to-SQL Translation with Execution Consistency | 2025 | SIGMOD |
| 6 | 10,732 | RTS+: Reliable Text to SQL | 2025 | SIGMOD |
| 7 | 10,556 | OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision | 2026 | VLDB |
| 8 | 6,936 | Reliable Text-to-SQL with Adaptive Abstention | 2025 | SIGMOD |
| 9 | 279 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB |
| 10 | 10,510 | NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions | 2026 | VLDB |