一句话：提出以日志变量为中心的 VISTA 策略，通过动态采样、变量缓存和自适应 ICL 提升 LLM 日志解析效率并降低成本。
日志解析从海量系统日志中提取结构化事件，是日志压缩、异常检测和故障诊断的基础。随着 LLM 的兴起，其文本理解与总结能力带来了更准确的日志解析，但现有基于 LLM 的方法主要关注日志常量，忽视日志变量的价值，导致采样、缓存和上下文学习效率不足。为此，作者提出以变量为中心的策略 VISTA，通过动态贡献采样、以变量为中心的缓存以及自适应变量感知的上下文学习，充分利用日志变量。早期结果显示，该方法提升了日志解析效率并显著降低了 LLM 使用成本。
Log parsing extracts structured events from massive system logs and is essential for tasks like compression, anomaly detection, and failure diagnosis. With the rise of LLMs, their strong text understanding and summarization capabilities have enabled more accurate log parsing. However, existing LLM-based methods mainly focus on log constants, overlooking the value of log variables, leading to inefficient sampling, cache use, and context learning. To address this, we propose a variable-centric strategy called VISTA, which fully leverages log variables through dynamic contribution sampling, variable-centric cache, and adaptive variable-aware ICL. Early results show improved parsing efficiency and significantly reduced LLM usage costs.
@inproceedings{paperbot9148,
title = {Exploring Variable Potential for LLM-based Log Parsing Efficiency and Reduced Costs},
author = {Jinrui Sun and Tong Jia and Minghua He and Yihan Wu and Ying Li and Gang Huang},
booktitle = {FSE},
year = {2025},
doi = {10.1145/3696630.3728506}
}