TED: Teaching AI to Explain its Decisions
This addresses the demand for explainable AI in deployed systems, offering a practical solution for consumers, though it appears incremental as it builds on existing explanation needs.
The paper tackles the problem of AI systems being opaque by proposing a new framework, TED, that provides explanations matching the consumer's mental model, resulting in highly accurate explanations without loss of prediction accuracy in two examples.
Artificial intelligence systems are being increasingly deployed due to their potential to increase the efficiency, scale, consistency, fairness, and accuracy of decisions. However, as many of these systems are opaque in their operation, there is a growing demand for such systems to provide explanations for their decisions. Conventional approaches to this problem attempt to expose or discover the inner workings of a machine learning model with the hope that the resulting explanations will be meaningful to the consumer. In contrast, this paper suggests a new approach to this problem. It introduces a simple, practical framework, called Teaching Explanations for Decisions (TED), that provides meaningful explanations that match the mental model of the consumer. We illustrate the generality and effectiveness of this approach with two different examples, resulting in highly accurate explanations with no loss of prediction accuracy for these two examples.