Exploring LLM Features in Predictive Process Monitoring for Small-Scale Event-Logs

This paper extends an LLM-based framework for Predictive Process Monitoring (PPM), evaluating its generality and reasoning mechanisms. It demonstrates that LLMs outperform benchmark methods in data-scarce settings for predicting process outcomes and activity occurrences. The research highlights LLMs' ability to leverage prior knowledge and internal correlations for higher-order reasoning, offering significant implications for improving operational efficiency in various processes.