Measures for explainable AI: Explanation goodness, user satisfaction, mental models, curiosity, trust, and human-AI performance
Florida Institute for Human and Machine Cognition · Michigan Technological University · +1 more institution
Abstract
If a user is presented an AI system that portends to explain how it works, how do we know whether the explanation works and the user has achieved a pragmatic understanding of the AI? This question entails some key concepts of measurement such as explanation goodness and trust. We present methods for enabling developers and researchers to: (1) Assess the a priori goodness of explanations, (2) Assess users' satisfaction with explanations, (3) Reveal user's mental model of an AI system, (4) Assess user's curiosity or need for explanations, (5) Assess whether the user's trust and reliance on the AI are appropriate, and finally, (6) Assess how the human-XAI work system performs. The methods we present derive from…
Citation impact
- FWCI
- 32.80
- Percentile
- 100%
- References
- 145
Authors
4Topics & keywords
- Curiosity
- Computer science
- Strengths and weaknesses
- Context (archaeology)
- Point (geometry)
- Goodness of fit
- Data science
- A priori and a posteriori