CelerLog dynamically routes logs to statistical or LLM processors based on pattern density, delivering leading accuracy on 14 datasets while being 7.9-18.6x faster than pure LLM parsers and cutting token use by 80-94%.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CelerLog: Fast Log Parsing via Dynamic Routing
CelerLog dynamically routes logs to statistical or LLM processors based on pattern density, delivering leading accuracy on 14 datasets while being 7.9-18.6x faster than pure LLM parsers and cutting token use by 80-94%.