A Measure of Explanatory Effectiveness
This work addresses the lack of consideration for the explainee in AI explanation methods, which is crucial for improving communication in AI systems.
The paper tackles the problem of explaining AI systems by proposing a measure of explanatory effectiveness based on a two-player cooperative game, focusing on the explainee's internal state to automate explanation assessment.
In most conversations about explanation and AI, the recipient of the explanation (the explainee) is suspiciously absent, despite the problem being ultimately communicative in nature. We pose the problem `explaining AI systems' in terms of a two-player cooperative game in which each agent seeks to maximise our proposed measure of explanatory effectiveness. This measure serves as a foundation for the automated assessment of explanations, in terms of the effects that any given action in the game has on the internal state of the explainee.