TY - JOUR
T1 - Defining Explanation and Explanatory Depth in XAI
AU - Buijsman, Stefan
PY - 2022
Y1 - 2022
N2 - Explainable artificial intelligence (XAI) aims to help people understand black box algorithms, particularly of their outputs. But what are these explanations and when is one explanation better than another? The manipulationist definition of explanation from the philosophy of science offers good answers to these questions, holding that an explanation consists of a generalization that shows what happens in counterfactual cases. Furthermore, when it comes to explanatory depth this account holds that a generalization that has more abstract variables, is broader in scope and/or more accurate is better. By applying these definitions and contrasting them with alternative definitions in the XAI literature I hope to help clarify what a good explanation is for AI.
AB - Explainable artificial intelligence (XAI) aims to help people understand black box algorithms, particularly of their outputs. But what are these explanations and when is one explanation better than another? The manipulationist definition of explanation from the philosophy of science offers good answers to these questions, holding that an explanation consists of a generalization that shows what happens in counterfactual cases. Furthermore, when it comes to explanatory depth this account holds that a generalization that has more abstract variables, is broader in scope and/or more accurate is better. By applying these definitions and contrasting them with alternative definitions in the XAI literature I hope to help clarify what a good explanation is for AI.
KW - Counterfactuals
KW - Explainability
KW - Explainable AI
KW - Manipulationism
UR - http://www.scopus.com/inward/record.url?scp=85133193612&partnerID=8YFLogxK
U2 - 10.1007/s11023-022-09607-9
DO - 10.1007/s11023-022-09607-9
M3 - Article
AN - SCOPUS:85133193612
VL - 32
SP - 563
EP - 584
JO - Minds and Machines: journal for artificial intelligence, philosophy and cognitive sciences
JF - Minds and Machines: journal for artificial intelligence, philosophy and cognitive sciences
SN - 0924-6495
IS - 3
ER -