A Multi-layered Approach for Tailored Black-box Explanations - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

A Multi-layered Approach for Tailored Black-box Explanations

(1, 2) , (2)
1
2

Abstract

Explanations for algorithmic decision systems can take different forms, they can target different types of users with different goals. One of the main challenges in this area is therefore to devise explanation methods that can accommodate this variety of situations. A first step to address this challenge is to allow explainees to express their needs in the most convenient way, depending on their level of expertise and motivation. In this paper, we present a solution to this problem based on a multi-layered approach allowing users to express their requests for explanations at different levels of abstraction. We illustrate the approach with the application of a proof-of-concept system called IBEX to two case studies.
Fichier principal
Vignette du fichier
IBEX_final_version.pdf (425.39 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03127926 , version 1 (01-02-2021)

Identifiers

Cite

Clément Henin, Daniel Le Métayer. A Multi-layered Approach for Tailored Black-box Explanations. ICPR 2020 - Workshop Explainable Deep Learning - AI, Jan 2021, Virtual Event, Italy. pp.5-19, ⟨10.1007/978-3-030-68796-0_1⟩. ⟨hal-03127926⟩
137 View
355 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More