Explaining arguments’ strength: unveiling the role of attacks and supports
File(s)
Accepted version
Author(s)
Yin, Xiang
Potyka, Nico
Toni, Francesca
Type
Conference Paper
Abstract
Quantitatively explaining the strength of arguments under gradual semantics has recently received increasing attention. Specifically, several works in the literature provide quantitative explanations by computing the attribution scores of arguments. These works disregard the importance of attacks and supports, even though they play an essential role when explaining arguments' strength. In this paper, we propose a novel theory of Relation Attribution Explanations (RAEs), adapting Shapley values from game theory to offer fine-grained insights into the role of attacks and supports in quantitative bipolar argumentation towards obtaining the arguments' strength. We show that RAEs satisfy several desirable properties. We also propose a probabilistic algorithm to approximate RAEs efficiently. Finally, we show the application value of RAEs in fraud detection and large language models case studies.
Date Issued
2024-08-03
Date Acceptance
2024-04-16
Citation
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024, pp.3622-3630
ISBN
978-1-956792-04-1
Publisher
International Joint Conferences on Artificial Intelligence
Start Page
3622
End Page
3630
Journal / Book Title
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence
Copyright Statement
Copyright © 2024 International Joint Conferences on Artificial Intelligence This is the author’s accepted manuscript made available under a CC-BY licence in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy)
License URL
Identifier
https://www.ijcai.org/proceedings/2024/0401
Source
IJCAI 2024, the 33rd International Joint Conference on Artificial Intelligence
Publication Status
Published
Start Date
2024-08-03
Finish Date
2024-08-09
Coverage Spatial
Jeju, South Korea
Date Publish Online
2024-08-03