Search papers, labs, and topics across Lattice.
This study evaluates the effectiveness of Concept Bottleneck Models (CBMs) as decision-support systems through two large-scale user studies involving 705 participants and 6,959 observations. The findings reveal that CBMs enhance the accuracy of human-AI teams, particularly in challenging classification tasks where users can interact with easily identifiable concepts. However, the benefits are contingent on specific conditions, such as the nature of the task and the accuracy of concept detection, which can influence user trust in the model.
CBMs can significantly boost human-AI collaboration accuracy, but only under the right conditions, highlighting the delicate balance between interpretability and trust.
Concept Bottleneck Models (CBMs) are interpretable-by-design neural networks that detect human-understandable concepts from the input and use them to generate predictions. By allowing users to inspect the concepts underlying a prediction and explore how predictions change under alternative concept configurations, CBMs have emerged as one of the most prominent approaches to supporting human-AI collaboration. However, user studies investigating their actual effectiveness as decision-support systems remain limited. We present two large-scale user studies (N participants = 705, N observations = 6,959) evaluating how concept-based explanations and user interventions on the model's concepts affect the performance of the human-AI team in two distinct binary classification tasks. Our results show that CBMs, and particularly their interactive component, can improve human-AI team accuracy relative to both unaided human performance and performance with non-interpretable AI support. However, these benefits emerge only under certain conditions: classification tasks perceived as difficult, easily identifiable concepts, and active interaction with the model. We also discuss how inaccurate concept detection may undermine users'trust in the model. Overall, this work provides practical guidance for the deployment of CBMs as effective decision-support tools.
