The Dialog Systems and Machine Learning group at Heinrich Heine University investigates fundamental questions in human–computer interaction, at the intersection of Natural Language Processing and Machine Learning. Our research focuses on building intelligent dialogue systems that can learn, reason, adapt, and interact effectively with humans in dynamic and uncertain environments. We develop principled methods for dialogue modelling, representation learning, reinforcement learning, knowledge acquisition, and user simulation. Our mission is to advance the foundations of machine intelligence towards dialogue systems that are adaptive, trustworthy, and genuinely useful to people.

This research is currently centred around the following key problems:

1. Trustworthy AI: How can we understand and quantify uncertainty in language models, and how do uncertainty, hallucination, emotions, and affective signals interact to shape the reliability of their outputs?
2. Representation learning: How can Topological Data Analysis reveal the structure and dynamics of representations learned by language models, providing a geometrical footprint of important machine learning phenomena?
3. Human-inspired intelligence: How can we equip artificial agents with Theory of Mind and human-inspired reward mechanisms, enabling them to reason about others’ mental states as well as their own, and learn more effectively from intrinsic signals such as pain, curiosity, and satisfaction?