Argumentative XAI: a survey
File(s)
Accepted version
Author(s)
Cyras, Kristijonas
Rago, Antonio
Emanuele, Albini
Baroni, Pietro
Toni, Francesca
Type
Conference Paper
Abstract
Explainable AI (XAI) has been investigated for decades and, together with AI itself, has witnessed unprecedented growth in recent years. Among various approaches to XAI, argumentative models have been advocated in both the AI and social science literature, as their dialectical nature appears to match some basic desirable features of the explanation activity. In this survey we overview XAI approaches built using methods from the field of computational argumentation, leveraging its wide array of reasoning abstractions and explanation delivery methods. We overview the literature focusing on different types of explanation (intrinsic and post-hoc), different models with which argumentation-based explanations are deployed, different forms of delivery, and different argumentation frameworks they use. We also lay out a roadmap for future work.
Date Issued
2021-08-19
Date Acceptance
2021-04-16
Citation
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021, pp.4392-4399
ISBN
9780999241196
Publisher
International Joint Conferences on Artificial Intelligence
Start Page
4392
End Page
4399
Journal / Book Title
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
Copyright Statement
© 2021 International Joint Conferences on Artificial Intelligence
Sponsor
Royal Academy Of Engineering
Grant Number
RCSRF2021\11\45
Source
The 30th International Joint Conference on Artificial Intelligence (IJCAI-21)
Subjects
cs.AI
cs.AI
Publication Status
Published
Start Date
2021-08-19
Finish Date
2021-08-27
Coverage Spatial
Montreal, Canada