Accéder directement au contenu Accéder directement à la navigation
Nouvelle interface
Communication dans un congrès

Identifying the "Right" Level of Explanation in a Given Situation

Abstract : We present a framework for defining the "right" level of AI explainability based on technical, legal and economic considerations. Our approach involves three logical steps: First, define the main con-textual factors, such as who is the audience of the explanation, the operational context, the level of harm that the system could cause, and the legal/regulatory framework. This step will help characterize the operational and legal needs for explanation, and the corresponding social benefits. Second, examine the technical tools available, including post-hoc approaches (input perturbation, saliency maps...) and hybrid AI approaches. Third, as function of the first two steps, choose the right levels of global and local explanation outputs, taking into the account the costs involved. We identify seven kinds of costs and emphasize that explanations are socially useful only when total social benefits exceed costs.
Type de document :
Communication dans un congrès
Liste complète des métadonnées

Littérature citée [26 références]  Voir  Masquer  Télécharger

https://hal.telecom-paris.fr/hal-02507316
Contributeur : David Bounie Connectez-vous pour contacter le contributeur
Soumis le : vendredi 13 mars 2020 - 08:11:29
Dernière modification le : samedi 22 octobre 2022 - 03:09:06
Archivage à long terme le : : dimanche 14 juin 2020 - 12:51:11

Fichiers

main.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-02507316, version 1

Collections

Citation

Valérie Beaudouin, Isabelle Bloch, David Bounie, Stéphan Clémençon, Florence d'Alché-Buc, et al.. Identifying the "Right" Level of Explanation in a Given Situation. First International Workshop on New Foundations for Human-Centered AI (NeHuAI), Sep 2020, Santiago de Compostella, Spain. pp.63. ⟨hal-02507316⟩

Partager

Métriques

Consultations de la notice

523

Téléchargements de fichiers

422