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.
@article{arxiv.2305.12233,
title = {A Measure of Explanatory Effectiveness},
author = {Dylan Cope and Peter McBurney},
journal= {arXiv preprint arXiv:2305.12233},
year = {2023}
}
Comments
Presented at the 1st International Workshop on Trusted Automated Decision-Making (TADM) co-located with ETAPS 2021