Research
I graduated with a PhD from the University of Ulm with a dissertation on the Design of Human-AI Interactions with Explainable Artificial Intelligence.
While I’m currently focused on my work in industry, I remain active in research as well to a small extent.
As of 2024, my research interests include:
- Long-term effects of explainable systems and implications for AI alignment
- Learning optimal user-centric explanations in real-world settings
- Effects of automated decision-making on organizations through the lens of (social) systems theory
As a researcher, I’m affiliated with the University of Ulm’s Institute of Business Analytics.
Publications Link to heading
-
Maximilian Förster, Philipp Hühn, Mathias Klier, Kilian Kluge: User-centric explainable AI: design and evaluation of an approach to generate coherent counterfactual explanations for structured data In: Journal of Decision Systems, September 6th, 2022
-
Kilian Kluge, Regina Eckhardt: Explaining the Suspicion: Design of an XAI-Based User-Focused Anti-Phishing Measure In: Wirtschaftsinformatik 2021 Proceedings, February 17th, 2021
-
Maximilian Förster, Philipp Hühn, Mathias Klier, Kilian Kluge: Capturing Users’ Reality: A Novel Approach to Generate Coherent Counterfactual Explanations In: Hawaii International Conference on System Sciences 2021, January 1st, 2021
-
Maximilian Förster, Mathias Klier, Kilian Kluge, Irina Sigler: Fostering Human Agency: A Process for the Design of User-Centric XAI Systems International Conference on Information Systems 2020, December 1st, 2020
-
Kilian Kluge, Regina Eckhardt: Explaining Suspected Phishing Attempts with Document Anchors In: 2020 ICML Workshop on Human Interpretability in Machine Learning, July 17th, 2020
-
Maximilian Förster, Mathias Klier, Kilian Kluge, Irina Sigler: Evaluating Explainable Artifical Intelligence – What Users Really Appreciate In: European Conference on Information Systems 2020, June 15th, 2020
Community involvement Link to heading
- Reviewer for the NeurIPS 2024 Workshop Interpretable AI: Past, Present and Future
- Reviewer for the NeurIPS 2023 Workshop XAI in Action: Past, Present, and Future Applications (XAIA)
- Reviewer for the 2020 ICML Workshop on Human Interpretability in Machine Learning (WHI)
- Reviewer for the IEEE Transactions on Engineering Management