Literature by the same author
plus at Google Scholar

Bibliografische Daten exportieren
 

A New Perspective on Evaluation Methods for Explainable Artificial Intelligence (XAI)

Title data

Speith, Timo ; Langer, Markus:
A New Perspective on Evaluation Methods for Explainable Artificial Intelligence (XAI).
In: Schneider, Kurt ; Dalpiaz, Fabiano ; Horkoff, Jennifer (ed.): 2023 IEEE 31st International Requirements Engineering Conference Workshops (REW). - Piscataway, NJ, USA : IEEE , 2023 . - pp. 325-331
ISBN 979-8-3503-2691-8
DOI: https://doi.org/10.1109/REW57809.2023.00061

Official URL: Volltext

Project information

Project financing: Deutsche Forschungsgemeinschaft
VolkswagenStiftung

Abstract in another language

One of the big challenges in the field of explainable artificial intelligence (XAI) is how to evaluate explainability approaches. Many evaluation methods (EMs) have been proposed, but a gold standard has yet to be established. Several authors classified EMs for explainability approaches into categories along aspects of the EMs themselves (e.g., heuristic-based, human-centered, application-grounded, functionally-grounded). In this vision paper, we propose that EMs can also be classified according to aspects of the XAI process they target. Building on models that spell out the main processes in XAI, we propose that there are explanatory information EMs, understanding EMs, and desiderata EMs. This novel perspective is intended to augment the perspective of other authors by focusing less on the EMs themselves but on what explainability approaches intend to achieve (i.e., provide good explanatory information, facilitate understanding, satisfy societal desiderata). We hope that the combination of the two perspectives will allow us to more comprehensively evaluate the advantages and disadvantages of explainability approaches, helping us to make a more informed decision about which approaches to use or how to improve them.

Further data

Item Type: Article in a book
Refereed: Yes
Keywords: Explainability; Explainable Artificial Intelligence; XAI; Evaluation; Evaluation Methods; Metrics; Studies
Institutions of the University: Faculties > Faculty of Cultural Studies > Department of Philosophy
Faculties > Faculty of Cultural Studies > Department of Philosophy > Chair Philosophy, Computer Science and Artificial Intelligence
Result of work at the UBT: Yes
DDC Subjects: 000 Computer Science, information, general works > 004 Computer science
100 Philosophy and psychology > 100 Philosophy
100 Philosophy and psychology > 150 Psychology
Date Deposited: 29 Apr 2024 07:38
Last Modified: 29 Apr 2024 07:38
URI: https://eref.uni-bayreuth.de/id/eprint/89426