Process Mining with LLMs

Summary

The post features David Obembe discussing his master’s thesis on creating a conversational interface for process‑mining tools using large language models (LLMs). He explains process mining fundamentals, how event logs become process maps, and how LLMs can speed up insight extraction by answering queries about bottlenecks and rework, evaluating performance with precision, recall and accuracy. The experiments show promising results and point to future improvements via Retrieval‑Augmented Generation.