The need for user models in generating expert system explanation

By R. Kass, Timothy W. Finin. 1988

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, neutral): “In their development of the GUMAC system, Kass and Finin (1988) assumed that an explanation must be appropriate and understandable for a particular user.”
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) (2018, background): “If we look back at the expert systems of the 80’s, we had what we would consider a scrutable system: an inference engine leveraged a knowledge base to make assertions that it could explain using the chain of reasoning that led to the assertion [56].”
A Survey on the Explainability of Supervised Machine Learning (2020, background): “the facets that an explanation should be short and highlight interesting aspects to the user, the explanation should also be simple so that the recipient does not have to look up too many unfamiliar terms (Kass and Finin, 1988).”
A Grounded Interaction Protocol for Explainable Artificial Intelligence (2019, background): “ssing the model with its contribution and significance in explainable AI. 2 RELATED WORK Explaining decisions of intelligent systems has been a topic of interest since the era of expert systems, e.g. [8, 18]. Early work focused particularly on the explanation’s content, responsiveness and the human-”