Explaining Explanations in AI

TL;DR

This paper discusses the limitations of simplified models in AI interpretability, emphasizing the importance of understanding explanations beyond these models and exploring broader philosophical perspectives to improve AI explanations.

Contribution

It highlights the distinction between interpretability models and explanations, proposing a broader view of explanations in AI inspired by philosophy and sociology.

Findings

Simplified models are useful but limited as explanations.

Different philosophical schools offer diverse perspectives on what constitutes an explanation.

Broader approaches could enhance AI interpretability and explanation methods.

Abstract

Recent work on interpretability in machine learning and AI has focused on the building of simplified models that approximate the true criteria used to make decisions. These models are a useful pedagogical device for teaching trained professionals how to predict what decisions will be made by the complex system, and most importantly how the system might break. However, when considering any such model it's important to remember Box's maxim that "All models are wrong but some are useful." We focus on the distinction between these models and explanations in philosophy and sociology. These models can be understood as a "do it yourself kit" for explanations, allowing a practitioner to directly answer "what if questions" or generate contrastive explanations without external assistance. Although a valuable ability, giving these models as explanations appears more difficult than necessary, and other forms of explanation may not have the same trade-offs. We contrast the different schools of thought on what makes an explanation, and suggest that machine learning might benefit from viewing the problem more broadly.