Project DetailsThis work tackles the challenge of monitoring anomalies in a running software, specifically by using a large language model (LLM) trained on the log file. This challenge can also be considered as a classification problem with two classes (anomaly, ‘normal’) with the log files as data. The project’s goal is to explore and measure possible improvements to the latest techniques. In pursuit of this goal, we have conducted a short literature review and then we started replicating results of common models and date databases.
