A Measure of Explanatory Effectiveness

TL;DR

This paper introduces a formal measure of explanatory effectiveness based on a cooperative game model, aiming to assess explanations' impact on the explainee's internal state for AI systems.

Contribution

It proposes a novel, game-theoretic measure of explanation quality that enables automated evaluation of explanations' effectiveness in AI.

Findings

Defines a measure of explanatory effectiveness

Models explanation as a cooperative game

Enables automated assessment of explanations

Abstract

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.