Considerations on explainable AI and users’ mental models
Heleen Rutjes, Martijn C. Willemsen, Wijnand A. IJsselsteijn · TU/e Research Portal · 2019
As the aim of explaining is understanding, XAI is successful when the user has a good understanding of the AI system. This paper shows, using theories from the social sciences and HCI, that appropriately capturing and accounting for the user’s mental model while explaining is key to successful XAI.