Abstract
Large language models (LLMs) have demonstrated promising performance in log anomaly detection, yet how their adaptation strategies, architectures, and deployment configurations affect detection effectiveness remains insufficiently understood. To investigate these factors, we conduct a systematic empirical analysis across three public log datasets, examining different adaptation strategies, model architectures, parameter scales, and quantization settings. Our results reveal substantial performance differences across adaptation strategies, while model scaling yields varying detection gains across datasets. We further observe that models with comparable detection accuracy can exhibit markedly different computational costs, and that low-bit quantization largely preserves detection performance in the evaluated configurations. Finally, we examine detection robustness under structural, semantic, and label noise at different perturbation levels. These findings provide empirical insights into the performance, efficiency, and robustness of LLM-based log anomaly detection, highlighting practical considerations beyond conventional accuracy-oriented evaluation.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Li, B., Wang, D., & Lu, S. (2026). Towards Understanding LLM-Based Log Anomaly Detection: An Empirical Study of Performance, Efficiency, and Robustness. https://omanscience.com/en/articles/towards-understanding-llm-based-log-anomaly-detection-an-empirical-study-of-performance-efficiency-and-robustness
MLA 9
Li, Bin, et al. "Towards Understanding LLM-Based Log Anomaly Detection: An Empirical Study of Performance, Efficiency, and Robustness." https://omanscience.com/en/articles/towards-understanding-llm-based-log-anomaly-detection-an-empirical-study-of-performance-efficiency-and-robustness.
Chicago (author–date)
Li, Bin, Dongdong Wang, and Siyang Lu. 2026. "Towards Understanding LLM-Based Log Anomaly Detection: An Empirical Study of Performance, Efficiency, and Robustness." https://omanscience.com/en/articles/towards-understanding-llm-based-log-anomaly-detection-an-empirical-study-of-performance-efficiency-and-robustness.
Harvard
Li, B., Wang, D. and Lu, S. (2026) 'Towards Understanding LLM-Based Log Anomaly Detection: An Empirical Study of Performance, Efficiency, and Robustness', Available at: https://omanscience.com/en/articles/towards-understanding-llm-based-log-anomaly-detection-an-empirical-study-of-performance-efficiency-and-robustness.
Vancouver
Li B, Wang D, Lu S. Towards Understanding LLM-Based Log Anomaly Detection: An Empirical Study of Performance, Efficiency, and Robustness. https://omanscience.com/en/articles/towards-understanding-llm-based-log-anomaly-detection-an-empirical-study-of-performance-efficiency-and-robustness
IEEE
B. Li, D. Wang, and S. Lu, "Towards Understanding LLM-Based Log Anomaly Detection: An Empirical Study of Performance, Efficiency, and Robustness," https://omanscience.com/en/articles/towards-understanding-llm-based-log-anomaly-detection-an-empirical-study-of-performance-efficiency-and-robustness.