Challenges of Explaining the Behavior of Black-Box AI Systems
Challenges of Explaining the Behavior of Black-Box AI Systems
Aleksandre Asatiani,P. Malo,3 Authors,Antti Salovaara
TLDR
Drawing on a case study at the Danish Business Authority, a framework and recommendations for addressing the many challenges of explaining the behavior of black-box AI systems will enable organizations to successfully develop and deploy AI systems without causing legal or ethical problems.
Abstract
There are many examples of problems resulting from inscrutable AI systems, so there is a growing need to be able to explain how such systems produce their outputs. Drawing on a case study at the Danish Business Authority, we provide a framework and recommendations for addressing the many challenges of explaining the behavior of black-box AI systems. Our findings will enable organizations to successfully develop and deploy AI systems without causing legal or ethical problems.(1,2)