Contestable AI needs Computational Argumentation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Leofante, Francesco, Ayoobi, Hamed, Dejl, Adam, Freedman, Gabriel, Gorur, Deniz, Jiang, Junqi, Paulino-Passos, Guilherme, Rago, Antonio, Rapberger, Anna, Russo, Fabrizio, Yin, Xiang, Zhang, Dekai, Toni, Francesca
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914537980035072
author Leofante, Francesco
Ayoobi, Hamed
Dejl, Adam
Freedman, Gabriel
Gorur, Deniz
Jiang, Junqi
Paulino-Passos, Guilherme
Rago, Antonio
Rapberger, Anna
Russo, Fabrizio
Yin, Xiang
Zhang, Dekai
Toni, Francesca
author_facet Leofante, Francesco
Ayoobi, Hamed
Dejl, Adam
Freedman, Gabriel
Gorur, Deniz
Jiang, Junqi
Paulino-Passos, Guilherme
Rago, Antonio
Rapberger, Anna
Russo, Fabrizio
Yin, Xiang
Zhang, Dekai
Toni, Francesca
contents AI has become pervasive in recent years, but state-of-the-art approaches predominantly neglect the need for AI systems to be contestable. Instead, contestability is advocated by AI guidelines (e.g. by the OECD) and regulation of automated decision-making (e.g. GDPR). In this position paper we explore how contestability can be achieved computationally in and for AI. We argue that contestable AI requires dynamic (human-machine and/or machine-machine) explainability and decision-making processes, whereby machines can (i) interact with humans and/or other machines to progressively explain their outputs and/or their reasoning as well as assess grounds for contestation provided by these humans and/or other machines, and (ii) revise their decision-making processes to redress any issues successfully raised during contestation. Given that much of the current AI landscape is tailored to static AIs, the need to accommodate contestability will require a radical rethinking, that, we argue, computational argumentation is ideally suited to support.
format Preprint
id arxiv_https___arxiv_org_abs_2405_10729
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Contestable AI needs Computational Argumentation
Leofante, Francesco
Ayoobi, Hamed
Dejl, Adam
Freedman, Gabriel
Gorur, Deniz
Jiang, Junqi
Paulino-Passos, Guilherme
Rago, Antonio
Rapberger, Anna
Russo, Fabrizio
Yin, Xiang
Zhang, Dekai
Toni, Francesca
Artificial Intelligence
AI has become pervasive in recent years, but state-of-the-art approaches predominantly neglect the need for AI systems to be contestable. Instead, contestability is advocated by AI guidelines (e.g. by the OECD) and regulation of automated decision-making (e.g. GDPR). In this position paper we explore how contestability can be achieved computationally in and for AI. We argue that contestable AI requires dynamic (human-machine and/or machine-machine) explainability and decision-making processes, whereby machines can (i) interact with humans and/or other machines to progressively explain their outputs and/or their reasoning as well as assess grounds for contestation provided by these humans and/or other machines, and (ii) revise their decision-making processes to redress any issues successfully raised during contestation. Given that much of the current AI landscape is tailored to static AIs, the need to accommodate contestability will require a radical rethinking, that, we argue, computational argumentation is ideally suited to support.
title Contestable AI needs Computational Argumentation
topic Artificial Intelligence
url https://arxiv.org/abs/2405.10729