Berlin, Germany — VIEWS Senior Researchers Paola Vesco, Simon Polichinel von der Maase, and Sonja Häffner participated in the 2025 Symposium on Crisis Early Warning, held on September 17–18, 2025, at the German Federal Foreign Office in Berlin. Co-organized with the Center for Crisis Early Warning (CCEW), the symposium focused on “The Potential of Data, AI, and Interdisciplinary Analysis in Situational Awareness and Decision Making.”
Paola Vesco chaired a panel on Advancing Methodological Approaches in Crisis Early Warning, featuring contributions from Thomas Chadefaux, Doctoral Candidate Chandler Williams, and a desk officer from the German Intelligence Agency. The session explored innovations in methodological design and the application of advanced analytics to crisis forecasting.
Simon Polichinel von der Maase attended as an expert on AI methodologies. His contribution focused on the responsible and effective integration of AI into early warning systems, emphasizing five core principles: the importance of specialized models, integration of user feedback, embedding forecasts into decision mechanisms, continuous collaboration with end users, and caution in the application of generic AI tools.
Sonja Häffner presented in the session “Pimp My Dataset – Enhancing Existing Event Datasets with Large Language Models”, co-led with Christian Oswald (Center for Crisis Early Warning, Munich). Together, they presented their research on how Large Language Models (LLMs), combined with human expertise, can be used to enrich existing conflict event datasets.
The interactive format fostered dialogue between practitioners and researchers on what types of information are most needed in practice, while also highlighting the current limitations of LLMs with regards to event extraction.