English

LEx: A Framework for Operationalising Layers of Machine Learning Explanations

Machine Learning 2021-04-21 v1 Artificial Intelligence Human-Computer Interaction

Abstract

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.

Keywords

Cite

@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}
}

Comments

6 pages

R2 v1 2026-06-24T01:20:56.917Z