LogTinyLLM: Tiny Large Language Models Based Contextual Log Anomaly Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909689922453504 |
|---|---|
| author | Ocansey, Isaiah Thompson Bhattacharya, Ritwik Sen, Tanmay |
| author_facet | Ocansey, Isaiah Thompson Bhattacharya, Ritwik Sen, Tanmay |
| contents | Log anomaly detection using traditional rule based or deep learning based methods is often challenging due to the large volume and highly complex nature of log sequence. So effective way of detection of anomalous sequence of logs is crucial for system maintenance and development. This paper proposes parameter efficient finetuning specifically low rank adaptation (LoRA) and adapter based approaches for finding contextual anomalies in sequence of logs in large log data set. It compares different tiny large language models (LLMs) on the Thunderbird dataset. The results show that LoRA based finetuning provides substantial performance improvements of 18 to 19 percentage over LogBert based full finetuning approach, achieving accuracy scores between 97.76% and 98.83% compared to 79.37%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_11071 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LogTinyLLM: Tiny Large Language Models Based Contextual Log Anomaly Detection Ocansey, Isaiah Thompson Bhattacharya, Ritwik Sen, Tanmay Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Log anomaly detection using traditional rule based or deep learning based methods is often challenging due to the large volume and highly complex nature of log sequence. So effective way of detection of anomalous sequence of logs is crucial for system maintenance and development. This paper proposes parameter efficient finetuning specifically low rank adaptation (LoRA) and adapter based approaches for finding contextual anomalies in sequence of logs in large log data set. It compares different tiny large language models (LLMs) on the Thunderbird dataset. The results show that LoRA based finetuning provides substantial performance improvements of 18 to 19 percentage over LogBert based full finetuning approach, achieving accuracy scores between 97.76% and 98.83% compared to 79.37%. |
| title | LogTinyLLM: Tiny Large Language Models Based Contextual Log Anomaly Detection |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.11071 |