Explanatory Pluralism in Explainable AI

TL;DR

This paper proposes a taxonomy of explanation types in AI to clarify the diverse interpretability needs and guide the development and evaluation of explainable AI methods.

Contribution

It introduces a pluralistic framework categorizing explanations into Diagnostic, Explication, Expectation, and Role types, clarifying their roles and evaluation criteria.

Findings

Provides a taxonomy of explanation types in XAI

Clarifies the purpose and evaluation of different explanation methods

Facilitates better alignment of explanations with stakeholder needs

Abstract

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.