Abstract
Explanation in Artificial Intelligence is often focused on providing reasons for why a model under consideration and its outcome are correct. Recently, research in explainable machine learning has initiated a shift in focus on including so-called counterfactual explanations. In this paper we propose to combine both types of explanation into a persuasive contrastive explanation that aims to provide an answer to the question Why outcome t instead of t'? posed by a user. In addition, we propose a model-agnostic algorithm for computing persuasive contrastive explanations from AI systems with few input variables.
Original language | English |
---|---|
Pages | 1-6 |
Number of pages | 6 |
Publication status | Published - 2021 |
Event | XLoKR 2021 - Duration: 3 Nov 2021 → 5 Nov 2021 |
Conference
Conference | XLoKR 2021 |
---|---|
Period | 3/11/21 → 5/11/21 |