Cognitive Perspectives on Context-based Decisions and Explanations
This work addresses the challenge of explainable AI for human users by bridging cognitive science insights with AI methods, though it appears incremental in applying existing cognitive models to an AI context.
The paper tackles the problem of making AI decisions understandable to humans by showing that the Contextual Importance and Utility (CIU) method for explainable AI aligns with action-oriented predictive representational structures from cognitive science, resulting in a tool that produces explanations humans can relate to and trust.
When human cognition is modeled in Philosophy and Cognitive Science, there is a pervasive idea that humans employ mental representations in order to navigate the world and make predictions about outcomes of future actions. By understanding how these representational structures work, we not only understand more about human cognition but also gain a better understanding for how humans rationalise and explain decisions. This has an influencing effect on explainable AI, where the goal is to provide explanations of computer decision-making for a human audience. We show that the Contextual Importance and Utility method for XAI share an overlap with the current new wave of action-oriented predictive representational structures, in ways that makes CIU a reliable tool for creating explanations that humans can relate to and trust.