CAISA Lab

Christian Nickel

PhD Student

Hello there, my name is Christian. I am fascinated by Artificial Intelligence, Deep Learning, and more specifically Natural Language Processing (NLP) and Large Language Models (LLMs), as well as their capabilities to understand and interact with humans. Moreover, I am a proponent of inter- and transdisciplinary research, bringing together expertise from diverse fields like psychology, Human-AI Interaction (HAI), Human-Computer Interaction (HCI), social sciences (economics, political science, sociology), and physics to overcome today’s limitations. I am passionate about identifying applications for cutting-edge research.

After receiving training in physics, economics, and political science at the University of Cologne, I completed my Master of Science in Computer Science and Bachelor of Science in Informatik (Major: Informatics / Computer Science, Minor: Psychology) at the University of Bonn. During my studies, I worked at the Fraunhofer Institute for Applied Information Technology (Fraunhofer FIT) on Distributed Ledger Technology (DLT), short: Blockchain, applications and at the Universities of Cologne and Bonn, focusing on communicating topics from Machine Learning, Human-Computer Interaction, and Cyber-Security to young academic talent. My Master’s thesis work dealt with emergent Theory of Mind-like capabilities in Large Language Models, exploring the extent to which such capabilities are influenced by perturbations in evaluation tasks and how they can be enhanced using alternative prompting techniques like Chain of Thought. We released a paper on this topic (arxiv-link) and will also present at the WiNLP workshop @ EMNLP 2024.

Building on these experiences, I am currently working at the interface of Artificial Intelligence and Human Cognition, building and evaluating systems of (multiple) socially-aware LLM agents by incorporating Theory of Mind. I look forward to collaborations with researchers and practitioners from all relevant fields. You can get in touch via (E-Mail) or (LinkedIn).