Publication Details

Download

Michael Chromik
reSHAPe: A Framework for Interactive Explanations in XAI Based on SHAP
In Proceedings of 18th European Conference on Computer-Supported Cooperative Work (ECSCW '20). European Society for Socially Embedded Technologies (EUSSET) (bib)

The interdisciplinary field of explainable artificial intelligence (XAI) aims to foster human understanding of black-box machine learning models through explanation-generating methods. In this paper, we describe the need for interactive explanation facilities for end-users in XAI. We believe that interactive explanation facilities that provide multiple layers of customizable explanations offer promising directions for empowering humans to practically understand model behavior and limitations. We outline a web-based UI framework for developing interactive explanation flows based on SHAP.