DivLog: Log Parsing with Prompt Enhanced In-Context Learning
Top Cited Papers
Open Access
- 12 April 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Abstract
Log parsing, which involves log template extraction from semi-structured logs to produce structured logs, is the first and the most critical step in automated log analysis. However, current log parsers suffer from limited effectiveness for two reasons. First, traditional data-driven log parsers solely rely on heuristics or handcrafted features designed by domain experts, which may not consistently perform well on logs from diverse systems. Second, existing supervised log parsers require model tuning, which is often limited to fixed training samples and causes sub-optimal performance across the entire log source. To address this limitation, we propose DivLog, an effective log parsing framework based on the in-context learning (ICL) ability of large language models (LLMs). Specifically, before log parsing, DivLog samples a small amount of offline logs as candidates by maximizing their diversity. Then, during log parsing, DivLog selects five appropriate labeled candidates as examples for each target log and constructs them into a prompt. By mining the semantics of examples in the prompt, DivLog generates a target log template in a training-free manner. In addition, we design a straightforward yet effective prompt format to extract the output and enhance the quality of the generated log templates. We conducted experiments on 16 widely-used public datasets. The results show that DivLog achieves (1) 98.1% Parsing Accuracy, (2) 92.1% Precision Template Accuracy, and (3) 92.9% Recall Template Accuracy on average, exhibiting state-of-the-art performance.Keywords
This publication has 35 references indexed in Scilit:
- Mining Historical Test Logs to Predict Bugs and Localize Faults in the Test Logs2019
- Tools and Benchmarks for Automated Log Parsing2019
- Drain: An Online Log Parsing Approach with Fixed Depth Tree2017
- Spell: Streaming Parsing of System Event Logs2016
- Experience Report: System Log Analysis for Anomaly Detection2016
- LogCluster - A data clustering and pattern mining algorithm for event logs2015
- Assisting developers of Big Data Analytics Applications when deploying on Hadoop clouds2013
- Speech recognition with deep recurrent neural networks2013
- Abstracting log lines to log event types for mining software system logs2010
- A data clustering algorithm for mining patterns from event logs2004