Several social factors impact how people respond to AI explanations used to justify AI decisions affecting them personally. In this position paper, we define a framework called the \textit{layers of explanation} (LEx), a lens through which we can assess the appropriateness of different types of explanations. The framework uses the notions of \textit{sensitivity} (emotional responsiveness) of features and the level of \textit{stakes} (decision's consequence) in a domain to determine whether different types of explanations are \textit{appropriate} in a given context. We demonstrate how to use the framework to assess the appropriateness of different types of explanations in different domains.
@article{arxiv.2104.09612,
title = {LEx: A Framework for Operationalising Layers of Machine Learning Explanations},
author = {Ronal Singh and Upol Ehsan and Marc Cheong and Mark O. Riedl and Tim Miller},
journal= {arXiv preprint arXiv:2104.09612},
year = {2021}
}