Saved in:
Bibliographic Details
Main Authors: Tsakalakis, Niko, Stalla-Bourdillon, Sophie, Huynh, Trung Dong, Moreau, Luc
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2206.04438
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913577465544704
author Tsakalakis, Niko
Stalla-Bourdillon, Sophie
Huynh, Trung Dong
Moreau, Luc
author_facet Tsakalakis, Niko
Stalla-Bourdillon, Sophie
Huynh, Trung Dong
Moreau, Luc
contents As automated decision-making solutions are increasingly applied to all aspects of everyday life, capabilities to generate meaningful explanations for a variety of stakeholders (i.e., decision-makers, recipients of decisions, auditors, regulators...) become crucial. In this paper, we present a taxonomy of explanations that was developed as part of a holistic 'Explainability-by-Design' approach for the purposes of the project PLEAD. The taxonomy was built with a view to produce explanations for a wide range of requirements stemming from a variety of regulatory frameworks or policies set at the organizational level either to translate high-level compliance requirements or to meet business needs. The taxonomy comprises nine dimensions. It is used as a stand-alone classifier of explanations conceived as detective controls, in order to aid supportive automated compliance strategies. A machinereadable format of the taxonomy is provided in the form of a light ontology and the benefits of starting the Explainability-by-Design journey with such a taxonomy are demonstrated through a series of examples.
format Preprint
id arxiv_https___arxiv_org_abs_2206_04438
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle A taxonomy of explanations to support Explainability-by-Design
Tsakalakis, Niko
Stalla-Bourdillon, Sophie
Huynh, Trung Dong
Moreau, Luc
Artificial Intelligence
Computers and Society
As automated decision-making solutions are increasingly applied to all aspects of everyday life, capabilities to generate meaningful explanations for a variety of stakeholders (i.e., decision-makers, recipients of decisions, auditors, regulators...) become crucial. In this paper, we present a taxonomy of explanations that was developed as part of a holistic 'Explainability-by-Design' approach for the purposes of the project PLEAD. The taxonomy was built with a view to produce explanations for a wide range of requirements stemming from a variety of regulatory frameworks or policies set at the organizational level either to translate high-level compliance requirements or to meet business needs. The taxonomy comprises nine dimensions. It is used as a stand-alone classifier of explanations conceived as detective controls, in order to aid supportive automated compliance strategies. A machinereadable format of the taxonomy is provided in the form of a light ontology and the benefits of starting the Explainability-by-Design journey with such a taxonomy are demonstrated through a series of examples.
title A taxonomy of explanations to support Explainability-by-Design
topic Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2206.04438