Explainable artificial intelligence (XAI), the goodness criteria and the grasp-ability test

By Tae Wan Kim. 2018

16 citations recorded by the source corpus.

This paper introduces the "grasp-ability test" as a "goodness" criteria by which to compare which explanation is more or less meaningful than others for users to understand the automated algorithmic data processing.

How researchers see this paper

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

1. Shane T. Mueller
2. Robert R. Hoffman
3. Gary Klein
4. Abigail Emrey
5. William J. Clancey
6. D. V. Carvalho
7. Eduardo Marques Pereira
8. Jaime S. Cardoso

Citations in the corpus

• Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, background): “Consonant with Hoffman, et al., Kim (2018) proposed that good explanations must not only be correct and accurate, but must enable the user to answer questions about the AI, especially counterfactual questions.”
• Machine Learning Interpretability: A Survey on Methods and Metrics (2019, background): “Therefore, it is argued that, when it comes to XAI, pragmatic theories of explanation are more appropriate than non-pragmatic ones [107].”