Back to papers
Leveraging Query Optimizers to Verify the Soundness of LLM-based Query Rewrites for Real-World Workloads, and More!
Summary: Empirical study on Microsoft SQL Server shows LLM-based query rewriting improves real-world workloads but cannot guarantee semantic equivalence. Propose a sound, efficient equivalence-checking technique leveraging optimizer capabilities and show LLM rewrites expose missing optimizer transformation rules.
(summarized by gpt-5-mini on Feb 09 2026)
- Paper ID
- 595
- Venue
- CIDR
- Year
- 2026
- Pagerank
- 4.1905499e-05
- Overall Rank
- 9,992 | 30.56%
- DOI
-
-
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank |
Citing Paper |
Year |
Venue |
Pagerank |
Outgoing Citations (Sorted by Pagerank)
Showing 24 of 24 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank |
Cited Paper |
Year |
Venue |
Pagerank |
| 71 |
How Good Are Query Optimizers, Really? |
2016 |
VLDB |
0.00059446482 |
| 640 |
Orthogonal Optimization of Subqueries and Aggregation |
2001 |
SIGMOD |
0.00018780632 |
| 659 |
The Making of TPC-DS |
2006 |
VLDB |
0.00018514913 |
| 662 |
Database Tuning Advisor for Microsoft SQL Server 2005 |
2004 |
VLDB |
0.00018478597 |
| 1,056 |
Cosette: An Automated Prover for SQL |
2017 |
CIDR |
0.00014391317 |
| 1,871 |
WinMagic : Subquery Elimination Using Window Aggregation |
2003 |
SIGMOD |
0.0001025746 |
| 2,097 |
Axiomatic Foundations and Algorithms for Deciding Semantic Equivalences of SQL Queries |
2018 |
VLDB |
9.5439744e-05 |
| 2,595 |
WeTune: Automatic Discovery and Verification of Query Rewrite Rules |
2022 |
SIGMOD |
8.4725961e-05 |
| 2,937 |
DSB: A Decision Support Benchmark for Workload-Driven and Traditional Database Systems |
2021 |
VLDB |
7.8552033e-05 |
| 3,241 |
A Learned Query Rewrite System using Monte Carlo Tree Search |
2022 |
VLDB |
7.32744e-05 |
| 3,276 |
Configuration-Parametric Query Optimization for Physical Design Tuning |
2008 |
SIGMOD |
7.2880761e-05 |
| 3,465 |
LLM-R2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency |
2025 |
VLDB |
7.0668293e-05 |
| 4,234 |
Panda: Performance Debugging for Databases using LLM Agents |
2024 |
CIDR |
6.3300159e-05 |
| 4,385 |
Proving Query Equivalence Using Linear Integer Arithmetic |
2023 |
SIGMOD |
6.2247394e-05 |
| 5,001 |
GenRewrite: Query Rewriting via Large Language Models |
2026 |
SIGMOD |
5.7634197e-05 |
| 5,245 |
QED: A Powerful Query Equivalence Decider for SQL |
2024 |
VLDB |
5.6017846e-05 |
| 5,533 |
QueryBooster: Improving SQL Performance Using Middleware Services for Human-Centered Query Rewriting |
2023 |
VLDB |
5.4555519e-05 |
| 6,671 |
Incorporating Super-Operators in Big-Data Query Optimizers |
2020 |
VLDB |
4.9625353e-05 |
| 7,030 |
R-Bot: An LLM-based Query Rewrite System |
2025 |
VLDB |
4.8518029e-05 |
| 7,203 |
Unified Query Optimization in the Fabric Data Warehouse |
2024 |
SIGMOD |
4.7968914e-05 |
| 8,020 |
User-Optimizer Communication using Abstract Plans in Sybase ASE |
2001 |
VLDB |
4.6005954e-05 |
| 8,847 |
Towards Foundation Database Models |
2025 |
CIDR |
4.4329366e-05 |
| 9,282 |
DBG-PT: A Large Language Model Assisted Query Performance Regression Debugger |
2024 |
VLDB |
4.3598981e-05 |
| 9,850 |
COMPARE: Accelerating Groupwise Comparison in Relational Databases for Data Analytics |
2021 |
VLDB |
4.2680295e-05 |
Semantically Similar Papers
| Overall Rank |
Paper |
Year |
Venue |
Pagerank |
| 11,292 |
Demo of QueryBooster: Supporting Middleware-Based SQL Query Rewriting as a Service |
2023 |
VLDB |
4.1905499e-05 |
| 10,144 |
Beyond Relational: Semantic-Aware Multi-Modal Analytics with LLM-Native Query Optimization |
2026 |
SIGMOD |
4.1905499e-05 |
| 7,351 |
Reliable Text-to-SQL with Adaptive Abstention |
2025 |
SIGMOD |
4.7484027e-05 |
| 366 |
Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation |
2024 |
VLDB |
0.00025580097 |
| 10,217 |
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 |
4.1905499e-05 |
| 7,030 |
R-Bot: An LLM-based Query Rewrite System |
2025 |
VLDB |
4.8518029e-05 |
| 5,429 |
Logical and Physical Optimizations for SQL Query Execution over Large Language Models |
2025 |
SIGMOD |
5.511638e-05 |
| 8,479 |
Can Large Language Models Be Query Optimizer for Relational Databases? |
2026 |
SIGMOD |
4.4967983e-05 |
| 3,465 |
LLM-R2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency |
2025 |
VLDB |
7.0668293e-05 |
| 5,001 |
GenRewrite: Query Rewriting via Large Language Models |
2026 |
SIGMOD |
5.7634197e-05 |