LLM Meets ML: Data-efficient Anomaly Detection on Unstable Logs
ACM Transactions on Software Engineering and Methodology · 31.08.2026 · 35 (8) · 1-48
DOI: 10.1145/3771283 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 16.07.2026. Verfasst von Fatemeh Hadadi und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 104 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada, Luxembourg National Research Fund.
Abstract (Originalsprache)
Most log-based anomaly detectors assume that logs are stable, although in reality they are often unstable due to software or environmental changes. Anomaly Detection on Unstable Logs (ULAD) is therefore a more realistic, yet under-investigated challenge. Current approaches predominantly employ Machine Learning (ML) models, which often require extensive labeled data for training. To mitigate data insufficiency, we propose FlexLog , a novel hybrid approach for ULAD that combines ML models—decision tree, k-nearest neighbors, and a feedforward neural network—with a Large Language Model (Mistral) through ensemble learning. FlexLog also incorporates a cache and Retrieval-Augmented Generation (RAG) to further enhance efficiency and effectiveness. To evaluate FlexLog , we configured four datasets for ULAD, namely ADFA-U, LOGEVOL-U, SynHDFS-U, and SYNEVOL-U. FlexLog outperforms all baselines by at least 1.2 percentage points (pp) in F1 score while using much less labeled data (62.87 pp reduction). When trained on the same amount of data as the baselines, FlexLog achieves up to a 13 pp increase in F1 score on ADFA-U across varying training dataset sizes. Additionally, FlexLog maintains inference time under one second per log sequence, making it suitable for most applications, except latency-sensitive systems. Further analysis reveals the positive impact of FlexLog ’s key components: cache, RAG, and ensemble learning.
Förderung
- Natural Sciences and Engineering Research Council of Canada
- Luxembourg National Research Fund
Zitieren
APA
Hadadi, F., Xu, Q., Bianculli, D., & Briand, L. (2026). LLM Meets ML: Data-efficient Anomaly Detection on Unstable Logs. ACM Transactions on Software Engineering and Methodology, 35(8), 1-48. https://doi.org/10.1145/3771283
Vancouver
Hadadi F, Xu Q, Bianculli D, Briand L. LLM Meets ML: Data-efficient Anomaly Detection on Unstable Logs. ACM Transactions on Software Engineering and Methodology. 2026;35(8):1-48. doi:10.1145/3771283
BibTeX
@article{Hadadi2026,
author = {Hadadi, Fatemeh and Xu, Qinghua and Bianculli, Domenico and Briand, Lionel},
title = {LLM Meets ML: Data-efficient Anomaly Detection on Unstable Logs},
journal = {ACM Transactions on Software Engineering and Methodology},
year = {2026},
volume = {35},
number = {8},
pages = {1--48},
doi = {10.1145/3771283}
}
EUVIMED