Counterfactual Explanations for Learning From Interpretation Transitions

<div> Counterfactual explanations are instrumental in helping humans gain insight into the decision-making processes of artificial intelligence systems by illustrating the effects of altering specific input variables. By presenting hypothetical scenarios, they foster transparency in artificial intelligence, enabling us to comprehend its operations more deeply and cultivate confidence in its dependability. This transparency is essential for the development of ethical artificial intelligence systems that are both equitable and accountable. In this paper, we expand upon the Learning From Interpretation Transitions framework by proposing a theoretical modeling of counterfactual explanations for dynamic multivalued logic programs. Furthermore, we introduce an efficient algorithm called CELOS that leverages properties over logic rules to compute all minimal counterfactual explanations. We show through theoretical results the correctness of our approaches. Practical evaluation is performed on benchmarks from biological literature and synthetic instances. </div>