The field of process mining and information extraction is experiencing a significant shift with the integration of large language models (LLMs). Recent studies have explored the potential of LLMs in adapting to process data, extracting patient information, and labelling event logs. The use of LLMs has shown promising results in improving predictive performance, reducing computational overhead, and enabling process mining in settings where traditional logs are missing. Notably, the development of novel frameworks and models has facilitated the extraction of structured information from unstructured data, such as sensor data and clinical narratives. The application of LLMs in these areas has the potential to revolutionize various industries, including healthcare and manufacturing. Noteworthy papers include: Domain Adaptation of LLMs for Process Data, which demonstrates the potential of LLMs in predictive process monitoring. IoT Miner: Intelligent Extraction of Event Logs from Sensor Data for Process Mining, which presents a novel framework for creating high-level event logs from raw industrial sensor data. Low-Resource Fine-Tuning for Multi-Task Structured Information Extraction with a Billion-Parameter Instruction-Tuned Model, which shows that well-tuned small models can deliver stable and accurate structured outputs at a fraction of the computational cost.