Defining Explanation and Explanatory Depth in XAI

Minds and Machines 32 (3):563-584 (2022)
  Copy   BIBTEX

Abstract

Explainable artificial intelligence (XAI) aims to help people understand black box algorithms, particularly of their outputs. But what are these explanations and when is one explanation better than another? The manipulationist definition of explanation from the philosophy of science offers good answers to these questions, holding that an explanation consists of a generalization that shows what happens in counterfactual cases. Furthermore, when it comes to explanatory depth this account holds that a generalization that has more abstract variables, is broader in scope and/or more accurate is better. By applying these definitions and contrasting them with alternative definitions in the XAI literature I hope to help clarify what a good explanation is for AI.

Links

PhilArchive



    Upload a copy of this work     Papers currently archived: 76,297

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

Explanatory Depth.Brad Weslake - 2010 - Philosophy of Science 77 (2):273-294.
What Should We Require from an Account of Explanation in Historiography?Veli Virmajoki - 2020 - Journal of the Philosophy of History 16 (1):22-53.
Explanation and the Explanatory Gap.Elanor Taylor - 2016 - Acta Analytica 31 (1):77-88.

Analytics

Added to PP
2022-06-29

Downloads
13 (#767,927)

6 months
11 (#82,574)

Historical graph of downloads
How can I increase my downloads?

Citations of this work

No citations found.

Add more citations