9 papers · 1 filter
Uncertainty Quantification as a Principled Foundation for Explainable Artificial Intelligence: A Case Study of Counterfactual Explanations
Kacper Sokol, Santo M. A. R. Thies, Eyke Hüllermeier
In this paper we argue that, to its detriment, transparency research overlooks many foundational concepts of artificial intelligence. As an illustrating example we focus on uncerta…
Perfect Counterfactuals in Imperfect Worlds: Modelling Noisy Implementation of Actions in Sequential Algorithmic Recourse
Yueqing Xuan, Kacper Sokol, Mark Sanderson +1
Algorithmic recourse suggests actions to individuals who have been adversely affected by automated decision-making, helping them to achieve the desired outcome. Knowing the recours…
Navigating Explanatory Multiverse Through Counterfactual Path Geometry
Kacper Sokol, Edward Small, Yueqing Xuan
Counterfactual explanations are the de facto standard when tasked with interpreting decisions of (opaque) predictive models. Their generation is often subject to technical and doma…
LIMEtree: Consistent and Faithful Surrogate Explanations of Multiple Classes
Kacper Sokol, Peter Flach
Explainable artificial intelligence provides tools to better understand predictive models and their decisions, but many such methods are limited to producing insights with respect…
Counterfactual Explanations for Clustering Models
Aurora Spagnol, Kacper Sokol, Pietro Barbiero +2
Clustering algorithms rely on complex optimisation processes that may be difficult to comprehend, especially for individuals who lack technical expertise. While many explainable ar…
Cross-model Fairness: Empirical Study of Fairness and Ethics Under Model Multiplicity
Kacper Sokol, Meelis Kull, Jeffrey Chan +1
While data-driven predictive models are a strictly technological construct, they may operate within a social context in which benign engineering choices entail implicit, indirect a…