🤖 AI Summary
The concept of “understanding” in eXplainable Artificial Intelligence (XAI) lacks a rigorous definition and formal theoretical foundation. Method: This paper addresses this gap through an interdisciplinary conceptual analysis and theoretical modeling approach—drawing on philosophy, psychology, linguistics, sociology, and computer science—and proposes the first dual-dimensional framework for understanding in XAI: *comprehension* (depth of cognitive grasp) and *enabledness* (capacity to act upon explanations), capturing their dynamic co-evolution and mutual dependence. Contribution/Results: It establishes user agency as the fundamental criterion for explanation success. Unlike data-driven models, the proposed framework yields a human-centered, evaluable, and evolution-aware taxonomy of understanding—providing foundational theoretical support for XAI explanation design, effectiveness evaluation, and human-AI collaborative decision-making.
📝 Abstract
Explainability has become an important topic in computer science and artificial intelligence, leading to a subfield called Explainable Artificial Intelligence (XAI). The goal of providing or seeking explanations is to achieve (better) 'understanding' on the part of the explainee. However, what it means to 'understand' is still not clearly defined, and the concept itself is rarely the subject of scientific investigation. This conceptual article aims to present a model of forms of understanding for XAI-explanations and beyond. From an interdisciplinary perspective bringing together computer science, linguistics, sociology, philosophy and psychology, a definition of understanding and its forms, assessment, and dynamics during the process of giving everyday explanations are explored. Two types of understanding are considered as possible outcomes of explanations, namely enabledness, 'knowing how' to do or decide something, and comprehension, 'knowing that' -- both in different degrees (from shallow to deep). Explanations regularly start with shallow understanding in a specific domain and can lead to deep comprehension and enabledness of the explanandum, which we see as a prerequisite for human users to gain agency. In this process, the increase of comprehension and enabledness are highly interdependent. Against the background of this systematization, special challenges of understanding in XAI are discussed.
