LogLLaMA: Transformer-based log anomaly detection with LLaMA
By: Zhuoyi Yang, Ian G. Harris
Potential Business Impact:
Finds computer problems by predicting normal messages.
Log anomaly detection refers to the task that distinguishes the anomalous log messages from normal log messages. Transformer-based large language models (LLMs) are becoming popular for log anomaly detection because of their superb ability to understand complex and long language patterns. In this paper, we propose LogLLaMA, a novel framework that leverages LLaMA2. LogLLaMA is first finetuned on normal log messages from three large-scale datasets to learn their patterns. After finetuning, the model is capable of generating successive log messages given previous log messages. Our generative model is further trained to identify anomalous log messages using reinforcement learning (RL). The experimental results show that LogLLaMA outperforms the state-of-the-art approaches for anomaly detection on BGL, Thunderbird, and HDFS datasets.
Similar Papers
Research on Cloud Platform Network Traffic Monitoring and Anomaly Detection System based on Large Language Models
Networking and Internet Architecture
Finds hidden problems in computer networks faster.
MADLLM: Multivariate Anomaly Detection via Pre-trained LLMs
Computation and Language
Finds weird patterns in data using smart text tricks.
System Log Parsing with Large Language Models: A Review
Machine Learning (CS)
Helps computers understand computer error messages better.