Forms of Understanding for XAI-Explanations
It addresses the foundational problem of defining understanding for researchers and practitioners in XAI, but it is incremental as it builds on existing interdisciplinary perspectives without introducing new empirical results or methods.
This conceptual article tackles the lack of a clear definition of 'understanding' in Explainable Artificial Intelligence (XAI) by proposing a model that distinguishes between enabledness ('knowing how') and comprehension ('knowing that') as outcomes of explanations, aiming to systematize forms of understanding for XAI-explanations and beyond.
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.