Explanatory Pluralism in Explainable AI
This work addresses the problem of unclear communication and evaluation in XAI for practitioners and stakeholders, offering a conceptual tool to improve clarity, though it is incremental as it builds on existing philosophical and technical ideas.
The paper tackles the ambiguity in the term 'explanation' in explainable AI by proposing a taxonomy of four types of explanations—Diagnostic, Explication, Expectation, and Role—based on different stakeholder needs and evaluative criteria, providing a framework to reduce confusion and guide evaluation.
The increasingly widespread application of AI models motivates increased demand for explanations from a variety of stakeholders. However, this demand is ambiguous because there are many types of 'explanation' with different evaluative criteria. In the spirit of pluralism, I chart a taxonomy of types of explanation and the associated XAI methods that can address them. When we look to expose the inner mechanisms of AI models, we develop Diagnostic-explanations. When we seek to render model output understandable, we produce Explication-explanations. When we wish to form stable generalizations of our models, we produce Expectation-explanations. Finally, when we want to justify the usage of a model, we produce Role-explanations that situate models within their social context. The motivation for such a pluralistic view stems from a consideration of causes as manipulable relationships and the different types of explanations as identifying the relevant points in AI systems we can intervene upon to affect our desired changes. This paper reduces the ambiguity in use of the word 'explanation' in the field of XAI, allowing practitioners and stakeholders a useful template for avoiding equivocation and evaluating XAI methods and putative explanations.