A Two-Dimensional Explanation Framework to Classify AI as Incomprehensible, Interpretable, or Understandable

Conference Paper (2021)
Author(s)

R.S. Verhagen (TU Delft - Interactive Intelligence)

M.A. Neerincx (TNO, TU Delft - Interactive Intelligence)

M.L. Tielman (TU Delft - Interactive Intelligence)

Research Group
Interactive Intelligence
Copyright
© 2021 R.S. Verhagen, M.A. Neerincx, M.L. Tielman
DOI related publication
https://doi.org/10.1007/978-3-030-82017-6_8
More Info
expand_more
Publication Year
2021
Language
English
Copyright
© 2021 R.S. Verhagen, M.A. Neerincx, M.L. Tielman
Research Group
Interactive Intelligence
Bibliographical Note
Accepted author manuscript@en
Pages (from-to)
119-138
ISBN (print)
978-3-030-82016-9
ISBN (electronic)
978-3-030-82017-6
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Because of recent and rapid developments in Artificial Intelligence (AI), humans and AI-systems increasingly work together in human-agent teams. However, in order to effectively leverage the capabilities of both, AI-systems need to be understandable to their human teammates. The branch of eXplainable AI (XAI) aspires to make AI-systems more understandable to humans, potentially improving human-agent teamwork. Unfortunately, XAI literature suffers from a lack of agreement regarding the definitions of and relations between the four key XAI-concepts: transparency, interpretability, explainability, and understandability. Inspired by both XAI and social sciences literature, we present a two-dimensional framework that defines and relates these concepts in a concise and coherent way, yielding a classification of three types of AI-systems: incomprehensible, interpretable, and understandable. We also discuss how the established relationships can be used to guide future research into XAI, and how the framework could be used during the development of AI-systems as part of human-AI teams.

Files

EXTRAAMAS2021_Verhagen_postpri... (pdf)
(pdf | 0.868 Mb)
- Embargo expired in 17-07-2022
License info not available