A fine-tuned LLM can generate valid execution plans that beat traditional and learned optimizers on three workloads, by distilling the best plans from multiple existing optimizers.
Nippon telegraph and telephone corporation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.DB 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Can Large Language Models Be Query Optimizer for Relational Databases?
A fine-tuned LLM can generate valid execution plans that beat traditional and learned optimizers on three workloads, by distilling the best plans from multiple existing optimizers.