AdaptiveLog: An Adaptive Log Analysis Framework with the Collaboration of Large and Small Language Model
Lipeng Ma, Weidong Yang, Yixuan Li, Ben Fei, Mingjie Zhou, Shuhao Li,, Sihang Jiang, Bo Xu, Yanghua Xiao

TL;DR
AdaptiveLog is a framework that combines small and large language models for log analysis, intelligently allocating tasks to optimize accuracy and reduce costs in automated system monitoring.
Contribution
It introduces an adaptive collaboration strategy between SLMs and LLMs, including an uncertainty-based selection and a retrieval-augmented prompting method for improved log analysis.
Findings
AdaptiveLog achieves state-of-the-art accuracy in log analysis tasks.
The framework significantly reduces LLM inference costs.
It effectively balances performance and efficiency in automated log analysis.
Abstract
Automated log analysis is crucial to ensure high availability and reliability of complex systems. The advent of LLMs in NLP has ushered in a new era of language model-driven automated log analysis, garnering significant interest. Within this field, two primary paradigms based on language models for log analysis have become prominent. Small Language Models (SLMs) follow the pre-train and fine-tune paradigm, focusing on the specific log analysis task through fine-tuning on supervised datasets. On the other hand, LLMs following the in-context learning paradigm, analyze logs by providing a few examples in prompt contexts without updating parameters. Despite their respective strengths, we notice that SLMs are more cost-effective but less powerful, whereas LLMs with large parameters are highly powerful but expensive and inefficient. To trade-off between the performance and inference costs of…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling
