What is understandable in Bayesian network explanations?
This addresses the need for better human-comprehensible explanations in AI systems for medical or expert users, but it is incremental as it builds on existing technical research without introducing new methods.
The paper tackles the problem of evaluating how well humans understand different explanation methods for Bayesian network predictions, particularly for physicians, by comparing four approaches through a survey with human participants.
Explaining predictions from Bayesian networks, for example to physicians, is non-trivial. Various explanation methods for Bayesian network inference have appeared in literature, focusing on different aspects of the underlying reasoning. While there has been a lot of technical research, there is very little known about how well humans actually understand these explanations. In this paper, we present ongoing research in which four different explanation approaches were compared through a survey by asking a group of human participants to interpret the explanations.