A Human-Centric Assessment Framework for AI
This addresses the problem of ensuring trustworthy AI for developers and users by providing a practical assessment method, though it is incremental as it builds on existing human-centric evaluation concepts.
The paper tackles the lack of standardized assessment for explainable AI systems by introducing a human-centric framework inspired by the Turing test, where domain experts evaluate AI solutions and explanations, and demonstrates it with two instantiations for classification accuracy and explanation usefulness.
With the rise of AI systems in real-world applications comes the need for reliable and trustworthy AI. An essential aspect of this are explainable AI systems. However, there is no agreed standard on how explainable AI systems should be assessed. Inspired by the Turing test, we introduce a human-centric assessment framework where a leading domain expert accepts or rejects the solutions of an AI system and another domain expert. By comparing the acceptance rates of provided solutions, we can assess how the AI system performs compared to the domain expert, and whether the AI system's explanations (if provided) are human-understandable. This setup -- comparable to the Turing test -- can serve as a framework for a wide range of human-centric AI system assessments. We demonstrate this by presenting two instantiations: (1) an assessment that measures the classification accuracy of a system with the option to incorporate label uncertainties; (2) an assessment where the usefulness of provided explanations is determined in a human-centric manner.