A typology of explanations for explainability-by-design
A typology of explanations for explainability-by-design
As automated decision-making permeates almost all aspects of everyday life, capabilities to generate meaningful explanations for various stakeholders (i.e., decision-makers, addressees of decisions including individuals, auditors, and regulators) should be carefully deployed. This paper presents a typology of explanations intended to support the first pillar of an explainability-by-design strategy. Its production has been achieved by pursuing a responsible innovation approach and introducing a new persona within the research and innovation process, i.e., a legal engineer, whose role is to work at the interface of two teams, the compliance and the engineering teams and to oversee the process of requirement elicitation, which is often opinionated and narrowing. Once explanation requirements have been derived from applicable regulatory requirements, compliance rules or business policies, they have been mapped to the dimensions of the typology to produce fine-grained explanation requirements, forming computable building blocks that can then be translated into system requirements during the technical design phase. The typology has been co-created with industry partners operating in two sectors: finance and education. Two pilot studies have thus been conducted to test both the feasibility of the generation and computation of explanations on the basis of the typology and the usefulness of the outputs in the light of the state of the art. The typology comprises nine hierarchical dimensions. It can be leveraged to operate a stand-alone classifier of explanations that acts as detective controls within a broader partially-automated compliance strategy. A machine-readable format of the typology is provided in the form of a light ontology.. A machine-readable format of the typology is provided in the form of a light ontology.
Tsakalakis, Niko
eae42e98-58b8-45b9-8c11-35a798cc9671
Stalla-Bourdillon, Sophie
c189651b-9ed3-49f6-bf37-25a47c487164
Huynh, Trung Dong
ddea6cf3-5a82-4c99-8883-7c31cf22dd36
Moreau, Luc
0b53974f-3e78-4c56-a47e-799d9f220911
Tsakalakis, Niko
eae42e98-58b8-45b9-8c11-35a798cc9671
Stalla-Bourdillon, Sophie
c189651b-9ed3-49f6-bf37-25a47c487164
Huynh, Trung Dong
ddea6cf3-5a82-4c99-8883-7c31cf22dd36
Moreau, Luc
0b53974f-3e78-4c56-a47e-799d9f220911
Tsakalakis, Niko, Stalla-Bourdillon, Sophie, Huynh, Trung Dong and Moreau, Luc
(2024)
A typology of explanations for explainability-by-design.
ACM Journal on Responsible Computing.
(In Press)
Abstract
As automated decision-making permeates almost all aspects of everyday life, capabilities to generate meaningful explanations for various stakeholders (i.e., decision-makers, addressees of decisions including individuals, auditors, and regulators) should be carefully deployed. This paper presents a typology of explanations intended to support the first pillar of an explainability-by-design strategy. Its production has been achieved by pursuing a responsible innovation approach and introducing a new persona within the research and innovation process, i.e., a legal engineer, whose role is to work at the interface of two teams, the compliance and the engineering teams and to oversee the process of requirement elicitation, which is often opinionated and narrowing. Once explanation requirements have been derived from applicable regulatory requirements, compliance rules or business policies, they have been mapped to the dimensions of the typology to produce fine-grained explanation requirements, forming computable building blocks that can then be translated into system requirements during the technical design phase. The typology has been co-created with industry partners operating in two sectors: finance and education. Two pilot studies have thus been conducted to test both the feasibility of the generation and computation of explanations on the basis of the typology and the usefulness of the outputs in the light of the state of the art. The typology comprises nine hierarchical dimensions. It can be leveraged to operate a stand-alone classifier of explanations that acts as detective controls within a broader partially-automated compliance strategy. A machine-readable format of the typology is provided in the form of a light ontology.. A machine-readable format of the typology is provided in the form of a light ontology.
Text
ssrn-5020690
- Version of Record
More information
Accepted/In Press date: 12 November 2024
Identifiers
Local EPrints ID: 496319
URI: http://eprints.soton.ac.uk/id/eprint/496319
ISSN: 2832-0565
PURE UUID: 8e0edfef-aae7-4947-ab5e-420092b7dceb
Catalogue record
Date deposited: 11 Dec 2024 18:00
Last modified: 14 Dec 2024 05:01
Export record
Contributors
Author:
Trung Dong Huynh
Author:
Luc Moreau
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics