Kacper Sokol

Kacper Sokol

Postdoc

Università della Svizzera italiana

Kacper Sokol is a postdoctoral researcher at the Faculty of Informatics, Università della Svizzera italiana (USI), affiliated with the People-Centered Computing Lab.

Research interests

His research primarily focuses on the explainability of data-driven predictive systems based on artificial intelligence and machine-learning algorithms, with a particular interest in their applications within the medical field.

Publications

Yueqing Xuan, Kacper Sokol, Mark Sanderson, Jeffrey Chan (2026). Diversity-Augmented Negative Sampling for Implicit Collaborative Filtering. Proceedings of the ACM Web Conference 2026, WWW 2026, Dubai, United Arab Emirates, originally scheduled for April 13-17, 2026, rescheduled for June 29 - July 3, 2026.

Kacper Sokol, Eyke Hüllermeier (2025). All You Need for Counterfactual Explainability Is Principled and Reliable Estimate of Aleatoric and Epistemic Uncertainty. CoRR.

Kacper Sokol, James C. Fackler, Julia E. Vogt (2025). Artificial intelligence should genuinely support clinical reasoning and decision making to bridge the translational gap. npj Digit. Medicine.

Kacper Sokol, James C. Fackler, Julia E. Vogt (2025). Artificial Intelligence Should Genuinely Support Clinical Reasoning and Decision Making To Bridge the Translational Gap. CoRR.

Yueqing Xuan, Edward Small, Kacper Sokol, Danula Hettiachchi, Mark Sanderson (2025). Comprehension is a double-edged sword: Over-interpreting unspecified information in intelligible machine learning explanations. Int. J. Hum. Comput. Stud..

Yueqing Xuan, Kacper Sokol, Mark Sanderson, Jeffrey Chan (2025). Diverse Negative Sampling for Implicit Collaborative Filtering. CoRR.

Yueqing Xuan, Kacper Sokol, Mark Sanderson, Jeffrey Chan (2025). Evaluating and Addressing Fairness Across User Groups in Negative Sampling for Recommender Systems. Proceedings of the 34th ACM International Conference on Information and Knowledge Management, CIKM 2025, Seoul, Republic of Korea, November 10-14, 2025.

Raúl Santos-Rodríguez, Kacper Sokol, Julia E. Vogt, Sven Wellmann (2025). From Research to Certification with Data-Driven Medical Decision Support Systems (Dagstuhl Seminar 25052). Dagstuhl Reports.

Edward A. Small, Wei Shao, Zeliang Zhang, Peihan Liu, Jeffrey Chan, Kacper Sokol, Flora D. Salim (2025). How robust is your fair model? Exploring the robustness of prominent fairness strategies. Data Min. Knowl. Discov..

Yueqing Xuan, Kacper Sokol, Mark Sanderson, Jeffrey Chan (2025). Leveraging Complementary AI Explanations to Mitigate Misunderstanding in XAI. IEEE Swiss Conference on Data Science, SDS 2025, Zürich, Switzerland, June 26-27, 2025.

Yueqing Xuan, Kacper Sokol, Mark Sanderson, Jeffrey Chan (2025). Leveraging Complementary AI Explanations to Mitigate Misunderstanding in XAI. CoRR.

Kacper Sokol, Edward Small, Yueqing Xuan (2025). Navigating explanatory multiverse through counterfactual path geometry. Mach. Learn..

Yueqing Xuan, Kacper Sokol, Mark Sanderson, Jeffrey Chan (2025). Perfect counterfactuals in imperfect worlds: modelling noisy implementation of actions in sequential algorithmic recourse. Mach. Learn..

Aurora Spagnol, Kacper Sokol, Pietro Barbiero, Marc Langheinrich, Martin Gjoreski (2024). Counterfactual Explanations for Clustering Models. CoRR.

Edward Small, Kacper Sokol, Daniel Manning, Flora D. Salim, Jeffrey Chan (2024). Equalised Odds is not Equal Individual Odds: Post-processing for Group and Individual Fairness. The 2024 ACM Conference on Fairness, Accountability, and Transparency, FAccT 2024, Rio de Janeiro, Brazil, June 3-6, 2024.

Kacper Sokol, Peter A. Flach (2024). Interpretable representations in explainable AI: from theory to practice. Data Min. Knowl. Discov..

Andreas Züfle, Flora D. Salim, Taylor Anderson, Matthew Scotch, Li Xiong, Kacper Sokol, Hao Xue, Ruochen Kong, David J. Heslop, Hye-Young Paik, C. Raina MacIntyre (2024). Leveraging Simulation Data to Understand Bias in Predictive Models of Infectious Disease Spread. ACM Trans. Spatial Algorithms Syst..

Yueqing Xuan, Kacper Sokol, Mark Sanderson, Jeffrey Chan (2024). Perfect Counterfactuals in Imperfect Worlds: Modelling Noisy Implementation of Actions in Sequential Algorithmic Recourse. CoRR.

Jose Maria Alonso-Moral, Zach Anthis, Rafael Berlanga, Alejandro Catalá, Philipp Cimiano, Peter A. Flach, Eyke Hüllermeier, Tim Miller, Oana Mitrut, Dimitry Mindlin, Gabriela Moise, Alin Moldoveanu, Florica Moldoveanu, Kacper Sokol, Aitor Soroa (2024). Proceedings of the First Multimodal, Affective and Interactive eXplainable AI Workshop (MAI-XAI24 2024) co-located with 27th European Conference On Artificial Intelligence 19-24 October 2024 (ECAI 2024), Santiago de Compostela, Spain, October 19, 2024. CEUR-WS.org.

Kacper Sokol, Julia E. Vogt (2024). What Does Evaluation of Explainable Artificial Intelligence Actually Tell Us? A Case for Compositional and Contextual Validation of XAI Building Blocks. Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, CHI EA 2024, Honolulu, HI, USA, May 11-16, 2024.

Kacper Sokol, Julia E. Vogt (2024). What Does Evaluation of Explainable Artificial Intelligence Actually Tell Us? A Case for Compositional and Contextual Validation of XAI Building Blocks. CoRR.

Kacper Sokol, Julia E. Vogt (2023). (Un)reasonable Allure of Ante-hoc Interpretability for High-stakes Domains: Transparency Is Necessary but Insufficient for Explainability. CoRR.

Yueqing Xuan, Edward Small, Kacper Sokol, Danula Hettiachchi, Mark Sanderson (2023). Can Users Correctly Interpret Machine Learning Explanations and Simultaneously Identify Their Limitations?. CoRR.

Edward A. Small, Jeffrey N. Clark, Christopher J. McWilliams, Kacper Sokol, Jeffrey Chan, Flora D. Salim, Raúl Santos-Rodríguez (2023). Counterfactual Explanations via Locally-guided Sequential Algorithmic Recourse. CoRR.

Edward A. Small, Kacper Sokol, Daniel Manning, Flora D. Salim, Jeffrey Chan (2023). Equalised Odds is not Equal Individual Odds: Post-processing for Group and Individual Fairness. CoRR.