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
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.SE 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
AnomalyGen synthesizes realistic labeled log sequences from source code via Log-Oriented Control Flow Graphs and LLM CoT verification to boost F1 scores of 12 anomaly detection models on HDFS and Zookeeper.
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%.
-
AnomalyGen: Enhancing Log-Based Anomaly Detection with Code-Guided Data Augmentation
AnomalyGen synthesizes realistic labeled log sequences from source code via Log-Oriented Control Flow Graphs and LLM CoT verification to boost F1 scores of 12 anomaly detection models on HDFS and Zookeeper.