Research Overview

Our team conducts research at the intersection of Data Science and Social Sciences with a focus on topics such as explainable & fair AI, AI robustness, AI auditing, AI alignment and safety in general.

The main focus topics of our research are:

  • Explainable AI and Interpretability: Research focusing on the explainability of AI models, offering local explanations for predictions, algorithmic recourse, and user-guided explainability.
  • Ethics and Fairness in AI: Studies discussing ethical implications of AI, with emphasis on balancing actionable explanations and the right to be forgotten, and ensuring fairness in accordance with European values.
  • Performance Evaluation, Efficiency, and Accountability of AI Models: Research discussing efficient strategies for evaluating and auditing AI models, especially those for evolving data streams, attribution methods, and data recovered from embedding spaces (through generative approaches).


  • February 2024: Our paper "Crowdsourcing is breaking my bank! A self-supervised Method for Fine-tuning Pre-trained Language models using Proximal Policy Optimization" by Shuo Yang and Gjergji Kasneci has been accepted at LREC-COLING 2024. A preprint is available on arXiv.
  • January 2024: Our work "I Prefer Not to Say: Protecting User Consent in Models with Optional Personal Data" by Tobias Leemann, Martin Pawelczyk, Christian Thomas Eberle, and Gjergji Kasneci was accepted as an Oral Presentation at AAAI-2024. A preprint is available on arXiv.
  • September 2023: We are happy to announce that our paper "Gaussian Membership Inference Privacy" by Tobias Leemann, Martin Pawelczyk, and Gjergji Kasneci has been accepted for publication at NeurIPS 2023. A preprint is available on arXiv.