LogLLaMA: Transformer-based log anomaly detection with LLaMA

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yang, Zhuoyi, Harris, Ian G.
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908275419643904
author Yang, Zhuoyi
Harris, Ian G.
author_facet Yang, Zhuoyi
Harris, Ian G.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_14849
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LogLLaMA: Transformer-based log anomaly detection with LLaMA
Yang, Zhuoyi
Harris, Ian G.
Machine Learning
Computation and Language
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.
title LogLLaMA: Transformer-based log anomaly detection with LLaMA
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2503.14849