An Evaluation of the Human-Interpretability of Explanation
This work addresses the problem of designing interpretable machine learning systems for users needing to understand predictions, though it is incremental in advancing understanding rather than introducing new methods.
The study investigated what makes explanations interpretable for users performing simulation, verification, and input-change tasks, finding that cognitive chunks impact performance more than variable repetitions, with consistent trends across tasks and domains.
Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions. However, exactly what kinds of explanation are truly human-interpretable remains poorly understood. This work advances our understanding of what makes explanations interpretable under three specific tasks that users may perform with machine learning systems: simulation of the response, verification of a suggested response, and determining whether the correctness of a suggested response changes under a change to the inputs. Through carefully controlled human-subject experiments, we identify regularizers that can be used to optimize for the interpretability of machine learning systems. Our results show that the type of complexity matters: cognitive chunks (newly defined concepts) affect performance more than variable repetitions, and these trends are consistent across tasks and domains. This suggests that there may exist some common design principles for explanation systems.