Explaining Model Confidence Using Counterfactuals
This work addresses the issue of trust in human-AI interaction for users by providing more interpretable confidence explanations, though it is incremental as it builds on existing counterfactual methods.
The paper tackles the problem of users needing to understand why AI models are confident in their predictions, showing that counterfactual explanations of confidence scores help study participants better understand and trust the model's predictions.
Displaying confidence scores in human-AI interaction has been shown to help build trust between humans and AI systems. However, most existing research uses only the confidence score as a form of communication. As confidence scores are just another model output, users may want to understand why the algorithm is confident to determine whether to accept the confidence score. In this paper, we show that counterfactual explanations of confidence scores help study participants to better understand and better trust a machine learning model's prediction. We present two methods for understanding model confidence using counterfactual explanation: (1) based on counterfactual examples; and (2) based on visualisation of the counterfactual space. Both increase understanding and trust for study participants over a baseline of no explanation, but qualitative results show that they are used quite differently, leading to recommendations of when to use each one and directions of designing better explanations.