Generality Is Not Enough: Zero-Label Cross-System Log-Based Anomaly Detection via Knowledge-Level Collaboration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Xinlong, Jia, Tong, He, Minghua, Li, Ying
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911255538696192
author Zhao, Xinlong
Jia, Tong
He, Minghua
Li, Ying
author_facet Zhao, Xinlong
Jia, Tong
He, Minghua
Li, Ying
contents Log-based anomaly detection is crucial for ensuring software system stability. However, the scarcity of labeled logs limits rapid deployment to new systems. Cross-system transfer has become an important research direction. State-of-the-art approaches perform well with a few labeled target logs, but limitations remain: small-model methods transfer general knowledge but overlook mismatches with the target system's proprietary knowledge; LLM-based methods can capture proprietary patterns but rely on a few positive examples and incur high inference cost. Existing LLM-small model collaborations route 'simple logs' to the small model and 'complex logs' to the LLM based on output uncertainty. In zero-label cross-system settings, supervised sample complexity is unavailable, and such routing does not consider knowledge separation. To address this, we propose GeneralLog, a novel LLM-small model collaborative method for zero-label cross-system log anomaly detection. GeneralLog dynamically routes unlabeled logs, letting the LLM handle 'proprietary logs' and the small model 'general logs,' enabling cross-system generalization without labeled target logs. Experiments on three public log datasets show that GeneralLog achieves over 90% F1-score under a fully zero-label setting, significantly outperforming existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2511_05882
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generality Is Not Enough: Zero-Label Cross-System Log-Based Anomaly Detection via Knowledge-Level Collaboration
Zhao, Xinlong
Jia, Tong
He, Minghua
Li, Ying
Software Engineering
Log-based anomaly detection is crucial for ensuring software system stability. However, the scarcity of labeled logs limits rapid deployment to new systems. Cross-system transfer has become an important research direction. State-of-the-art approaches perform well with a few labeled target logs, but limitations remain: small-model methods transfer general knowledge but overlook mismatches with the target system's proprietary knowledge; LLM-based methods can capture proprietary patterns but rely on a few positive examples and incur high inference cost. Existing LLM-small model collaborations route 'simple logs' to the small model and 'complex logs' to the LLM based on output uncertainty. In zero-label cross-system settings, supervised sample complexity is unavailable, and such routing does not consider knowledge separation. To address this, we propose GeneralLog, a novel LLM-small model collaborative method for zero-label cross-system log anomaly detection. GeneralLog dynamically routes unlabeled logs, letting the LLM handle 'proprietary logs' and the small model 'general logs,' enabling cross-system generalization without labeled target logs. Experiments on three public log datasets show that GeneralLog achieves over 90% F1-score under a fully zero-label setting, significantly outperforming existing methods.
title Generality Is Not Enough: Zero-Label Cross-System Log-Based Anomaly Detection via Knowledge-Level Collaboration
topic Software Engineering
url https://arxiv.org/abs/2511.05882