Towards Federated LLM-Powered CEP Rule Generation and Refinement

Majid Lotfian Delouee, Daria G. Pernes, Victoria Degeler, Boris Koldehofe

Abstract: In traditional event processing systems, patterns representing situations of interest are typically defined by domain experts or learned from historical data, making rule generation reactive, time-consuming, and susceptible to human error. This paper proposes integrating large language models (LLMs) to automate and accelerate query translation and rule generation into event-based systems. Also, we introduce a federated learning schema to refine the initially generated rules by examining them over distributed event streams, ensuring greater accuracy and adaptability. Preliminary results demonstrate the potential of LLMs as a key component in proactively expediting the autonomous rule-generation process. Moreover, our findings suggest that employing customized prompt engineering techniques can further enhance the quality of the generated rules.