Logical and Physical Optimizations for SQL Query Execution over Large Language Models
Summary: Galois sits between SQL and LLMs, using LLMs as a storage layer with LLM-aware physical operators. LLM-focused optimization with dynamic metadata beats conventional plans, delivering up to 144% quality gains vs NL questions and 29% vs SQL. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Dario Satriani (University of Basilicata)
- 2. Enzo Veltri (University of Basilicata)
- 3. Donatello Santoro (University of Basilicata)
- 4. Sara Rosato (EURECOM)
- 5. Simone Varriale (EURECOM)
- 6. Paolo Papotti (EURECOM)
BibTeX Citation
@inproceedings{satriani_sigmod25,
title = {{Logical and Physical Optimizations for SQL Query Execution over Large Language Models}},
author = {Satriani, Dario and Veltri, Enzo and Santoro, Donatello and Rosato, Sara and Varriale, Simone and Papotti, Paolo},
series = {{SIGMOD} '25},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3725411},
url = {https://dl.acm.org/doi/10.1145/3725411},
year = {2025}
}
Incoming Citations (Sorted by Pagerank)
Showing 10 of 10 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 18 of 18 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next