Are Contrastive Explanations Useful?

James Forrest; Somayajulu Sripada; Wei Pang; George Coghill

Are Contrastive Explanations Useful?

James Forrest, Somayajulu Sripada, Wei Pang, George Coghill

Research output: Contribution to journal › Conference article › peer-review

1 Citation (Scopus)

91 Downloads (Pure)

Abstract

From the user perspective (data subjects and data controllers), useful explanations of ML decisions are selective, contrastive and social. In this paper, we describe an algorithm for generating selective and contrastive explanations and experimentally study its usefulness to users.

Original language	English
Pages (from-to)	9-16
Number of pages	8
Journal	CEUR Workshop Proceedings
Volume	2894
Publication status	Published - 2 Jul 2021
Event	SICSA Workshop on eXplainable Artificial Intelligence 2021 - Aberdeen, United Kingdom Duration: 1 Jun 2021 → 1 Jun 2021

Keywords

Contrastive explanations
Interpretable ML
XAI

ASJC Scopus subject areas

General Computer Science

Access to Document

Download pdf
Copyright © 2021 for this paper by its authors.
Final published version, 554 KBLicence: CC BY

http://ceur-ws.org/Vol-2894/short2.pdfLicence: CC BY

Cite this

@article{c706d5043c4043abac6f174fec5c42f6,

title = "Are Contrastive Explanations Useful?",

abstract = "From the user perspective (data subjects and data controllers), useful explanations of ML decisions are selective, contrastive and social. In this paper, we describe an algorithm for generating selective and contrastive explanations and experimentally study its usefulness to users.",

keywords = "Contrastive explanations, Interpretable ML, XAI",

author = "James Forrest and Somayajulu Sripada and Wei Pang and George Coghill",

note = "Funding Information: ★ Supported by EPSRC DTP Grant Number EP/N509814/1 Copyright {\textcopyright} 2021 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). Publisher Copyright: Copyright {\textcopyright} 2021 for this paper by its authors.; SICSA Workshop on eXplainable Artificial Intelligence 2021, SICSA XAI Workshop 2021 ; Conference date: 01-06-2021 Through 01-06-2021",

year = "2021",

month = jul,

day = "2",

language = "English",

volume = "2894",

pages = "9--16",

journal = "CEUR Workshop Proceedings",