A Measure of Explanatory Effectiveness

Dylan Cope; Peter McBurney

A Measure of Explanatory Effectiveness

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

35 Downloads (Pure)

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.

Original language	English
Title of host publication	The 1st International Workshop on Trusted Automated Decision-Making (TADM) co-located with ETAPS 2021
Publication status	Published - 2021

Access to Document

COPE_MCBURNEY_A_Measure_of_Explanatory_Effectiveness__LNCS_Format_

Cite this

@inbook{45f4e76abbef4f54a442b73e591a3e0c,

title = "A Measure of Explanatory Effectiveness",

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.",

author = "Dylan Cope and Peter McBurney",

year = "2021",

language = "English",

booktitle = "The 1st International Workshop on Trusted Automated Decision-Making (TADM) co-located with ETAPS 2021",

}

TY - CHAP

T1 - A Measure of Explanatory Effectiveness

AU - Cope, Dylan

AU - McBurney, Peter

PY - 2021

Y1 - 2021

N2 - 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.

AB - 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.

M3 - Conference paper

BT - The 1st International Workshop on Trusted Automated Decision-Making (TADM) co-located with ETAPS 2021

ER -

A Measure of Explanatory Effectiveness

Abstract

Access to Document

Fingerprint

Cite this