Explainability in Artificial Intelligence (AI) has been revived as a topic of active research by the need of conveying safety and trust to users in the “how” and “why” of automated decision‐making in different applications such as autonomous driving, medical diagnosis, or banking and finance. While explainability in AI has recently received significant attention, the origins of this line of work go back several decades to when AI systems were mainly developed as (knowledge‐based) expert systems. Since then, the definition, understanding, and implementation of explainability have been picked up in several lines of research work, namely, expert systems, machine learning, recommender systems, and in approaches to neural‐symbolic learning and reasoning, mostly happening during different periods of AI history. In this article, we present a historical perspective of Explainable Artificial Intelligence. We discuss how explainability was mainly conceived in the past, how it is understood in the present and, how it might be understood in the future. We conclude the article by proposing criteria for explanations that we believe will play a crucial role in the development of human‐understandable explainable systems.This article is categorized under: Fundamental Concepts of Data and Knowledge > Explainable AI Technologies > Artificial Intelligence

The assessment of explanations by humans presents a significant challenge within the context of Explainable and Trustworthy AI. This is attributed not only to the absence of universal metrics and standardized evaluation methods, but also to complexities tied to devising user studies that assess the perceived human comprehensibility of these explanations. To address this gap, we introduce a survey-based methodology for guiding the human evaluation of explanations. This approach amalgamates leading practices from existing literature and is implemented as an operational framework. This framework assists researchers throughout the evaluation process, encompassing hypothesis formulation, online user study implementation and deployment, and analysis and interpretation of collected data. The application of this framework is exemplified through two practical user studies.

Axiom weakening is a novel technique that allows for fine-grained repair of inconsistent ontologies. In a multi-agent setting, integrating ontologies corresponding to multiple agents may lead to inconsistencies. Such inconsistencies can be resolved after the integrated ontology has been built, or their generation can be prevented during ontology generation. We implement and compare these two approaches. First, we study how to repair an inconsistent ontology resulting from a voting-based aggregation of views of heterogeneous agents. Second, we prevent the generation of inconsistencies by letting the agents engage in a turn-based rational protocol about the axioms to be added to the integrated ontology. We instantiate the two approaches using real-world ontologies and compare them by measuring the levels of satisfaction of the agents w.r.t. the ontology obtained by the two procedures.