A Means-End Account of Explainable Artificial Intelligence

TL;DR

This paper applies means-end epistemology to structure and evaluate explainable AI by linking explanation topics, stakeholders, and goals with appropriate methods, offering a comprehensive framework for understanding and assessing XAI approaches.

Contribution

It introduces a means-end account of XAI that provides both a descriptive taxonomy and normative criteria for selecting suitable explanation methods.

Findings

Provides a taxonomy of XAI contributions based on means-end relations

Proposes normative criteria for evaluating XAI methods

Highlights the importance of aligning explanation topics, stakeholders, and goals

Abstract

Explainable artificial intelligence (XAI) seeks to produce explanations for those machine learning methods which are deemed opaque. However, there is considerable disagreement about what this means and how to achieve it. Authors disagree on what should be explained (topic), to whom something should be explained (stakeholder), how something should be explained (instrument), and why something should be explained (goal). In this paper, I employ insights from means-end epistemology to structure the field. According to means-end epistemology, different means ought to be rationally adopted to achieve different epistemic ends. Applied to XAI, different topics, stakeholders, and goals thus require different instruments. I call this the means-end account of XAI. The means-end account has a descriptive and a normative component: on the one hand, I show how the specific means-end relations give rise to a taxonomy of existing contributions to the field of XAI; on the other hand, I argue that the suitability of XAI methods can be assessed by analyzing whether they are prescribed by a given topic, stakeholder, and goal.