2022/07/30 by Guilherme Paulino-Passos, Francesca Toni, Paulino-Passos, Guilherme +1 · 1 citation
Computer Science · #Advanced Database Systems and Queries #Artificial Intelligence (cs.AI) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Semantic Web and Ontologies
paper · pdf · doi:10.48550/arxiv.2208.00316
openalex publication_date 2022/07/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Recent work shows issues of consistency with explanations, with methods generating local explanations that seem reasonable instance-wise, but that are inconsistent across instances. This suggests not only that instance-wise explanations can be unreliable, but mainly that, when interacting with a system via multiple inputs, a user may actually lose confidence in the system. To better analyse this issue, in this work we treat explanations as objects that can be subject to reasoning and present a formal model of the interactive scenario between user and system, via sequences of inputs, outputs, and explanations. We argue that explanations can be thought of as committing to some model behaviour (even if only prima facie), suggesting a form of entailment, which, we argue, should be thought of as non-monotonic. This allows: 1) to solve some considered inconsistencies in explanation, such as via a specificity relation; 2) to consider properties from the non-monotonic reasoning literature and discuss their desirability, gaining more insight on the interactive explanation scenario.