用小模型+高效微调检测日志异常，准确率超97%
LogTinyLLM: Tiny Large Language Models Based Contextual Log Anomaly Detection
- 采用低秩适配（LoRA）和适配器方法，轻量微调小规模大语言模型
- 在Thunderbird数据集上达到97.76%~98.83%准确率，较全参数微调提升18-19个百分点
- 适合资源有限场景下的日志异常实时检测，尤其适合运维与系统监控
基于传统规则或深度学习的日志异常检测因日志序列数量庞大且结构复杂而面临挑战。本文提出一种基于参数高效微调的上下文异常检测方法，重点采用低秩适配（LoRA）和适配器机制，在大规模日志数据集上对多个小型大语言模型（Tiny LLMs）进行评估。实验在Thunderbird数据集上进行，结果表明，基于LoRA的微调方法相比基于LogBert的全参数微调，性能提升达18至19个百分点，准确率从79.37%提高至97.76%至98.83%之间，显著提升了检测效果。
原文摘要 · Abstract (English)
Log anomaly detection using traditional rule based or deep learning based methods is often challenging due to the large volume and highly complex nature of log sequence. So effective way of detection of anomalous sequence of logs is crucial for system maintenance and development. This paper proposes parameter efficient finetuning specifically low rank adaptation (LoRA) and adapter based approaches for finding contextual anomalies in sequence of logs in large log data set. It compares different tiny large language models (LLMs) on the Thunderbird dataset. The results show that LoRA based finetuning provides substantial performance improvements of 18 to 19 percentage over LogBert based full finetuning approach, achieving accuracy scores between 97.76% and 98.83% compared to 79.37%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。