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
594
Venue
CIDR
Year
2026
Pagerank
5.093636e-05
Overall Rank
10,139 | 30.44%
DOI
-
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
@inproceedings{narasayya_cidr26,
address = {Amsterdam, Netherlands},
series = {{CIDR} '26},
title = {{Leveraging Query Optimizers to Verify the Soundness of LLM-based Query Rewrites for Real-World Workloads, and More!}},
booktitle = {Proceedings of the {Conference} on {Innovative} {Data} {Systems} {Research}},
author = {Narasayya, Vivek and Chaudhuri, Surajit},
year = {2026}
}
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
Rank
Citing Paper
Year
Venue
Pagerank
PreviousPage 1 / 1Next
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.