Even-if Explanations: Formal Foundations, Priorities and Complexity
This work addresses the need for more interpretable and user-centric AI explanations, particularly for semifactual queries, though it is incremental in building on existing explainability research.
The paper tackles the problem of local post-hoc explainability in AI by focusing on semifactual 'even-if' explanations, showing that linear and tree-based models are more interpretable than neural networks, and introducing a preference-based framework to personalize explanations with algorithms for polynomial cases.
EXplainable AI has received significant attention in recent years. Machine learning models often operate as black boxes, lacking explainability and transparency while supporting decision-making processes. Local post-hoc explainability queries attempt to answer why individual inputs are classified in a certain way by a given model. While there has been important work on counterfactual explanations, less attention has been devoted to semifactual ones. In this paper, we focus on local post-hoc explainability queries within the semifactual `even-if' thinking and their computational complexity among different classes of models, and show that both linear and tree-based models are strictly more interpretable than neural networks. After this, we introduce a preference-based framework that enables users to personalize explanations based on their preferences, both in the case of semifactuals and counterfactuals, enhancing interpretability and user-centricity. Finally, we explore the complexity of several interpretability problems in the proposed preference-based framework and provide algorithms for polynomial cases.