Kasneci, Gjergji

27 publications

CHIL 2025 ALPEC: A Comprehensive Evaluation Framework and Dataset for Machine Learning-Based Arousal Detection in Clinical Practice Stefan Kraft, Andreas Theissler, Dr. Vera Wienhausen-Wilke, Philipp Walter, Gjergji Kasneci, Hendrik Lensch

TMLR 2025 Attention Mechanisms Don’t Learn Additive Models: Rethinking Feature Importance for Transformers Tobias Leemann, Alina Fastowski, Felix Pfeiffer, Gjergji Kasneci

TMLR 2025 Explanation Shift: How Did the Distribution Shift Impact the Model? Carlos Mougan, Klaus Broelemann, Gjergji Kasneci, Thanassis Tiropanis, Steffen Staab

ICML 2025 Graph Inverse Style Transfer for Counterfactual Explainability Bardh Prenkaj, Efstratios Zaradoukas, Gjergji Kasneci

ICML 2025 Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers Roman Abramov, Felix Steinbauer, Gjergji Kasneci

ICML 2025 Position: Uncertainty Quantification Needs Reassessment for Large Language Model Agents Michael Kirchhof, Gjergji Kasneci, Enkelejda Kasneci

AAAI 2025 RAZOR: Sharpening Knowledge by Cutting Bias with Unsupervised Text Rewriting Shuo Yang, Bardh Prenkaj, Gjergji Kasneci

ICML 2025 SCISSOR: Mitigating Semantic Bias Through Cluster-Aware Siamese Networks for Robust Classification Shuo Yang, Bardh Prenkaj, Gjergji Kasneci

ICLRW 2025 Sycophancy Claims About Language Models: The Missing Human-in-the-Loop Jan Batzner, Volker Stocker, Stefan Schmid, Gjergji Kasneci

AAAI 2024 I Prefer Not to Say: Protecting User Consent in Models with Optional Personal Data Tobias Leemann, Martin Pawelczyk, Christian Thomas Eberle, Gjergji Kasneci

ICMLW 2024 Is My Data Safe? Predicting Instance-Level Membership Inference Success for White-Box and Black-Box Attacks Tobias Leemann, Bardh Prenkaj, Gjergji Kasneci

NeurIPSW 2023 Caution to the Exemplars: On the Intriguing Effects of Example Choice on Human Trust in XAI Tobias Leemann, Yao Rong, Thai-Trang Nguyen, Enkelejda Kasneci, Gjergji Kasneci

NeurIPS 2023 Gaussian Membership Inference Privacy Tobias Leemann, Martin Pawelczyk, Gjergji Kasneci

AAAI 2023 Interventional SHAP Values and Interaction Values for Piecewise Linear Regression Trees Artjom Zern, Klaus Broelemann, Gjergji Kasneci

ICLR 2023 Language Models Are Realistic Tabular Data Generators Vadim Borisov, Kathrin Sessler, Tobias Leemann, Martin Pawelczyk, Gjergji Kasneci

ICLR 2023 On the Trade-Off Between Actionable Explanations and the Right to Be Forgotten Martin Pawelczyk, Tobias Leemann, Asia Biega, Gjergji Kasneci

ICLR 2023 Probabilistically Robust Recourse: Navigating the Trade-Offs Between Costs and Robustness in Algorithmic Recourse Martin Pawelczyk, Teresa Datta, Johan Van den Heuvel, Gjergji Kasneci, Himabindu Lakkaraju

UAI 2023 When Are Post-Hoc Conceptual Explanations Identifiable? Tobias Leemann, Michael Kirchhof, Yao Rong, Enkelejda Kasneci, Gjergji Kasneci

ICML 2022 A Consistent and Efficient Evaluation Strategy for Attribution Methods Yao Rong, Tobias Leemann, Vadim Borisov, Gjergji Kasneci, Enkelejda Kasneci

ICLRW 2022 Coherence Evaluation of Visual Concepts with Objects and Language Tobias Leemann, Yao Rong, Stefan Kraft, Enkelejda Kasneci, Gjergji Kasneci

NeurIPSW 2022 Explanation Shift: Detecting Distribution Shifts on Tabular Data via the Explanation Space Carlos Mougan, Klaus Broelemann, Gjergji Kasneci, Thanassis Tiropanis, Steffen Staab

NeurIPSW 2022 On the Trade-Off Between Actionable Explanations and the Right to Be Forgotten Martin Pawelczyk, Tobias Leemann, Asia Biega, Gjergji Kasneci

NeurIPSW 2021 A Robust Unsupervised Ensemble of Feature-Based Explanations Using Restricted Boltzmann Machines Vadim Borisov, Johannes Meier, Johan Van den Heuvel, Hamed Jalali, Gjergji Kasneci

UAI 2020 On Counterfactual Explanations Under Predictive Multiplicity Martin Pawelczyk, Klaus Broelemann, Gjergji. Kasneci

AAAI 2020 Training Decision Trees as Replacement for Convolution Layers Wolfgang Fuhl, Gjergji Kasneci, Wolfgang Rosenstiel, Enkelejda Kasneci

IJCAI 2019 A Gradient-Based Split Criterion for Highly Accurate and Transparent Model Trees Klaus Broelemann, Gjergji Kasneci

ECML-PKDD 2010 Bayesian Knowledge Corroboration with Logical Rules and User Feedback Gjergji Kasneci, Jurgen Van Gael, Ralf Herbrich, Thore Graepel