2.1AISep 21, 2023
On the Definition of Appropriate Trust and the Tools that Come with itHelena Löfström
Evaluating the efficiency of human-AI interactions is challenging, including subjective and objective quality aspects. With the focus on the human experience of the explanations, evaluations of explanation methods have become mostly subjective, making comparative evaluations almost impossible and highly linked to the individual user. However, it is commonly agreed that one aspect of explanation quality is how effectively the user can detect if the predictions are trustworthy and correct, i.e., if the explanations can increase the user's appropriate trust in the model. This paper starts with the definitions of appropriate trust from the literature. It compares the definitions with model performance evaluation, showing the strong similarities between appropriate trust and model performance evaluation. The paper's main contribution is a novel approach to evaluating appropriate trust by taking advantage of the likenesses between definitions. The paper offers several straightforward evaluation methods for different aspects of user performance, including suggesting a method for measuring uncertainty and appropriate trust in regression.
Fast Calibrated Explanations: Efficient and Uncertainty-Aware Explanations for Machine Learning ModelsTuwe Löfström, Fatima Rabia Yapicioglu, Alessandra Stramiglio et al.
This paper introduces Fast Calibrated Explanations, a method designed for generating rapid, uncertainty-aware explanations for machine learning models. By incorporating perturbation techniques from ConformaSight - a global explanation framework - into the core elements of Calibrated Explanations (CE), we achieve significant speedups. These core elements include local feature importance with calibrated predictions, both of which retain uncertainty quantification. While the new method sacrifices a small degree of detail, it excels in computational efficiency, making it ideal for high-stakes, real-time applications. Fast Calibrated Explanations are applicable to probabilistic explanations in classification and thresholded regression tasks, where they provide the likelihood of a target being above or below a user-defined threshold. This approach maintains the versatility of CE for both classification and probabilistic regression, making it suitable for a range of predictive tasks where uncertainty quantification is crucial.