发表机构
University of Trento; CIMeC, University of Trento; DISI, University of Trento（特伦托大学; 特伦托大学认知科学与技术中心; 特伦托大学信息工程与计算机科学系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过两项大规模用户研究，发现概念瓶颈模型（CBMs）的交互组件可在特定条件下提升人机团队二分类任务准确率，为其作为决策支持工具的部署提供实用指导。
AI 中文摘要
概念瓶颈模型（CBMs）是天生可解释的神经网络，可从输入中检测人类可理解的概念并利用这些概念生成预测。通过允许用户检查预测背后的概念，并探究在不同概念配置下预测的变化，CBMs已成为支持人机协作的最突出方法之一。然而，针对其作为决策支持系统实际有效性的用户研究仍有限。我们开展两项大规模用户研究（参与者数量N=705，观测数量N=6959），评估基于概念的解释及用户对模型概念的干预如何影响人机团队在两项不同二分类任务中的表现。结果显示，CBMs，尤其是其交互组件，相比无辅助的人类表现及使用不可解释AI支持的表现，可提升人机团队的准确率。但这些益处仅在特定条件下出现：任务被感知为困难、概念易于识别、且与模型进行主动交互。我们还探讨了不准确的概念检测可能如何损害用户对模型的信任。总体而言，本研究为将CBMs部署为有效的决策支持工具提供了实用指导。
英文摘要
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.
