Saved in:
Bibliographic Details
Main Authors: Zhang, Wei, Guan, Xiangyuan, Yunhong, Lu, Zhang, Jie, Song, Shuangyong, Cheng, Xianfu, Wu, Zhenhe, Li, Zhoujun
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.18205
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910893717061632
author Zhang, Wei
Guan, Xiangyuan
Yunhong, Lu
Zhang, Jie
Song, Shuangyong
Cheng, Xianfu
Wu, Zhenhe
Li, Zhoujun
author_facet Zhang, Wei
Guan, Xiangyuan
Yunhong, Lu
Zhang, Jie
Song, Shuangyong
Cheng, Xianfu
Wu, Zhenhe
Li, Zhoujun
contents Logs produced by extensive software systems are integral to monitoring system behaviors. Advanced log analysis facilitates the detection, alerting, and diagnosis of system faults. Log parsing, which entails transforming raw log messages into structured templates, constitutes a critical phase in the automation of log analytics. Existing log parsers fail to identify the correct templates due to reliance on human-made rules. Besides, these methods focus on statistical features while ignoring semantic information in log messages. To address these challenges, we introduce a cutting-edge \textbf{L}og parsing framework with \textbf{E}ntropy sampling and chain-of-thought \textbf{M}erging (\model{}). Specifically, to discard the tedious manual rules, we propose a novel sampling method inspired by information entropy, which efficiently clusters typical logs. Furthermore, to enhance the merging of log templates, we design a chain-of-thought method for large language models (LLMs). LLMs exhibit exceptional semantic comprehension and deftly distinguish between parameters and invariant tokens. We have conducted experiments on large-scale public datasets. Extensive evaluation demonstrates that \model{} achieves state-of-the-art performance and impressive efficiency. The Code is available at https://github.com/zwpride/lemur.
format Preprint
id arxiv_https___arxiv_org_abs_2402_18205
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Lemur: Log Parsing with Entropy Sampling and Chain-of-Thought Merging
Zhang, Wei
Guan, Xiangyuan
Yunhong, Lu
Zhang, Jie
Song, Shuangyong
Cheng, Xianfu
Wu, Zhenhe
Li, Zhoujun
Software Engineering
Artificial Intelligence
Logs produced by extensive software systems are integral to monitoring system behaviors. Advanced log analysis facilitates the detection, alerting, and diagnosis of system faults. Log parsing, which entails transforming raw log messages into structured templates, constitutes a critical phase in the automation of log analytics. Existing log parsers fail to identify the correct templates due to reliance on human-made rules. Besides, these methods focus on statistical features while ignoring semantic information in log messages. To address these challenges, we introduce a cutting-edge \textbf{L}og parsing framework with \textbf{E}ntropy sampling and chain-of-thought \textbf{M}erging (\model{}). Specifically, to discard the tedious manual rules, we propose a novel sampling method inspired by information entropy, which efficiently clusters typical logs. Furthermore, to enhance the merging of log templates, we design a chain-of-thought method for large language models (LLMs). LLMs exhibit exceptional semantic comprehension and deftly distinguish between parameters and invariant tokens. We have conducted experiments on large-scale public datasets. Extensive evaluation demonstrates that \model{} achieves state-of-the-art performance and impressive efficiency. The Code is available at https://github.com/zwpride/lemur.
title Lemur: Log Parsing with Entropy Sampling and Chain-of-Thought Merging
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2402.18205