Argumentative debates for transparent bias detection
File(s)
Author(s)
Ayoobi, Hamed
Potyka, Nico
Rapberger, Anna
Toni, Francesca
Type
Conference Paper
Abstract
As the use of AI in society grows, addressing emerging biases is essential to prevent systematic discrimination. Several bias detection methods have been proposed, but, with few exceptions, these tend to ignore transparency. Instead, interpretability and explainability are core requirements for algorithmic fairness, even more so than for other algorithmic solutions, given the human-oriented nature of fairness. We present ABIDE (Argumentative BIas detection by DEbate), a novel framework that structures bias detection transparently as debate, guided by an underlying argument graph as understood in (formal and computational) argumentation. The arguments are about the success chances of groups in local neighbourhoods and the significance of these neighbourhoods. We evaluate ABIDE experimentally and demonstrate its strengths in performance against an argumentative baseline.
Date Issued
2026-03-14
Date Acceptance
2025-11-07
Citation
Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence, 2026, 40 (23), pp.18944-18952
ISBN
978-1-57735-906-7
ISSN
2159-5399
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Start Page
18944
End Page
18952
Journal / Book Title
Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence
Volume
40
Issue
23
Copyright Statement
Copyright © 2026, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
Source
Fortieth AAAI Conference on Artificial Intelligence
Publication Status
Published
Start Date
2026-01-20
Finish Date
2026-01-27
Coverage Spatial
Singapore
Date Publish Online
2026-03-14