Understanding XAI Through the Philosopher's Lens: A Historical Perspective

TL;DR

This paper explores the philosophical foundations of explainable AI by examining historical developments in philosophy of science, revealing parallels with AI's evolution from deterministic to probabilistic models of explanation.

Contribution

It bridges philosophy of science and AI, providing a novel epistemological perspective on the concept of explanation in XAI and highlighting their parallel paradigm shifts.

Findings

Both domains evolved from logical-deductive to statistical explanations.

Similar concepts like explanation, understanding, and pragmatic factors emerged independently.

A paradigm shift from deterministic to probabilistic causality occurred in both fields.

Abstract

Despite explainable AI (XAI) has recently become a hot topic and several different approaches have been developed, there is still a widespread belief that it lacks a convincing unifying foundation. On the other hand, over the past centuries, the very concept of explanation has been the subject of extensive philosophical analysis in an attempt to address the fundamental question of "why" in the context of scientific law. However, this discussion has rarely been connected with XAI. This paper tries to fill in this gap and aims to explore the concept of explanation in AI through an epistemological lens. By comparing the historical development of both the philosophy of science and AI, an intriguing picture emerges. Specifically, we show that a gradual progression has independently occurred in both domains from logical-deductive to statistical models of explanation, thereby experiencing in both cases a paradigm shift from deterministic to nondeterministic and probabilistic causality. Interestingly, we also notice that similar concepts have independently emerged in both realms such as, for example, the relation between explanation and understanding and the importance of pragmatic factors. Our study aims to be the first step towards understanding the philosophical underpinnings of the notion of explanation in AI, and we hope that our findings will shed some fresh light on the elusive nature of XAI.