Unlearning spurious correlations (TMLR)
Machine learning models often rely on spurious correlations — features that are strongly associated with class labels but lack any causal connection. For exa...
Welcome to the Chair for Artificial Intelligence at the University of Marburg and the Hessian Center for Artificial Intelligence, lead by Prof. Dr. Christin Seifert. Our mission is to advance the development of trustworthy AI systems designed for practical use. Our team specializes in creating explainable and user-centric AI, advancing natural language processing, and solving real-world problems with machine learning.
Recent Posts
Knowledge Editing in Large Language Models (NAACL’25)
In our ever-changing world, knowledge of language models (LLMs) needs to be constantly updated. Facts change and LLMs need to reflect this.
LLMs for Generating and Evaluating Counterfactuals (EMNLP’24)
“What minimal changes to this text would cause the text classifier to change its prediction?” Counterfactual texts, i.e. minimal changes to inputs that alter...
InfoLossQA – Characterizing and Recovering Information Loss in Text Simplification (ACL’24)
Text simplification aims to make texts more accessible to a broader audience. Simplification, however, is inherently a lossy process. Additionally, one simpl...