Skip to main content

Research Repository

Advanced Search

Towards feasible counterfactual explanations: a taxonomy guided template-based NLG method.

Salimi, Pedram; Wiratunga, Nirmalie; Corsar, David; Wijekoon, Anjana

Authors



Contributors

Kobi Gal
Editor

Ann Nowé
Editor

Grzegorz J. Nalepa
Editor

Roy Fairstein
Editor

Roxana Rădulescu
Editor

Abstract

Counterfactual Explanations (cf-XAI) describe the smallest changes in feature values necessary to change an outcome from one class to another. However, many cf-XAI methods neglect the feasibility of those changes. In this paper, we introduce a novel approach for presenting cf-XAI in natural language (Natural-XAI), giving careful consideration to actionable and comprehensible aspects while remaining cognizant of immutability and ethical concerns. We present three contributions to this endeavor. Firstly, through a user study, we identify two types of themes present in cf-XAI composed by humans: content-related, focusing on how features and their values are included from both the counterfactual and the query perspectives; and structure-related, focusing on the structure and terminology used for describing necessary value changes. Secondly, we introduce a feature actionability taxonomy with four clearly defined categories, to streamline the explanation presentation process. Using insights from the user study and our taxonomy, we created a generalisable template-based natural language generation (NLG) method compatible with existing explainers like DICE, NICE, and DisCERN, to produce counterfactuals that address the aforementioned limitations of existing approaches. Finally, we conducted a second user study to assess the performance of our taxonomy-guided NLG templates on three domains. Our findings show that the taxonomy-guided Natural-XAI approach (n-XAIT) received higher user ratings across all dimensions, with significantly improved results in the majority of the domains assessed for articulation, acceptability, feasibility, and sensitivity dimensions.

Citation

SALIMI, P., WIRATUNGA, N., CORSAR, D. and WIJEKOON, A. 2023. Towards feasible counterfactual explanations: a taxonomy guided template-based NLG method. In Gal, K., Nowé, A., Nalepa, G.J., Fairstein, R. and Rădulescu, R. (eds.) ECAI 2023: proceedings of the 26th European conference on artificial intelligence (ECAI 2023), 30 September - 4 October 2023, Kraków, Poland. Frontiers in artificial intelligence and applications, 372. Amsterdam: IOS Press [online], pages 2057-2064. Available from: https://doi.org/10.3233/FAIA230499

Conference Name 26th European conference on artificial intelligence 2023 (ECAI-2023)
Conference Location Krakow, Poland
Start Date Sep 30, 2023
End Date Oct 5, 2023
Acceptance Date Jul 15, 2023
Online Publication Date Sep 28, 2023
Publication Date Dec 31, 2023
Deposit Date Jul 20, 2023
Publicly Available Date Aug 8, 2023
Publisher IOS Press
Pages 2057-2064
Series Title Frontiers in artificial intelligence and applications
Series Number 372
Series ISSN 0922-6389; 1879-8314
Book Title ECAI 2023: proceedings of the 26th European conference on artificial intelligence (ECAI 2023), 30 September - 4 October 2023, Kraków, Poland
ISBN 9781643684369
DOI https://doi.org/10.3233/faia230499
Keywords Counterfactual explanation; Natural-XAI method; Feature actionability taxonomy (FAT); Actionability knowledge;
Public URL https://rgu-repository.worktribe.com/output/2015280

Files

SALIMI 2023 Towards feasible counterfactual (VOR) (745 Kb)
PDF

Publisher Licence URL
https://creativecommons.org/licenses/by-nc/4.0/

Copyright Statement
© 2023 The Authors. This article is published online with Open Access by IOS Press and distributed under the terms of the Creative Commons Attribution Non-Commercial License 4.0 (CC BY-NC 4.0).






You might also like



Downloadable Citations