Argumentative Debates for Transparent Bias Detection [Technical Report]

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ayoobi, Hamed, Potyka, Nico, Rapberger, Anna, Toni, Francesca
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917085235380224
author Ayoobi, Hamed
Potyka, Nico
Rapberger, Anna
Toni, Francesca
author_facet Ayoobi, Hamed
Potyka, Nico
Rapberger, Anna
Toni, Francesca
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_04511
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Argumentative Debates for Transparent Bias Detection [Technical Report]
Ayoobi, Hamed
Potyka, Nico
Rapberger, Anna
Toni, Francesca
Artificial Intelligence
Machine Learning
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.
title Argumentative Debates for Transparent Bias Detection [Technical Report]
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2508.04511