Capturing Users’ Reality: A Novel Approach to Generate Coherent Counterfactual Explanations

Abstract

The opacity of Artificial Intelligence (AI) systems is a major impediment to their deployment. Explainable AI (XAI) methods that automatically generate counterfactual explanations for AI decisions can increase users’ trust in AI systems. Coherence is an essential property of explanations but is not yet addressed sufficiently by existing XAI methods. We design a novel optimization-based approach to generate coherent counterfactual explanations, which is applicable to numerical, categorical, and mixed data. We demonstrate the approach in a realistic setting and assess its efficacy in a human-grounded evaluation. Results suggest that our approach produces explanations that are perceived as coherent as well as suitable to explain the factual situation.