CBM通过可解释概念提升人机协作决策准确率，但需满足特定条件。
Are Concept Bottleneck Models Effective as Decision-Support Systems?
- 基于人类可理解的概念进行预测，支持用户交互干预。
- 在困难任务中，人机团队准确率高于纯人或非可解释AI。
- 需概念易识别且用户主动参与，否则可能降低信任度。
概念瓶颈模型（CBMs）是设计上可解释的神经网络，从输入中检测人类可理解的概念并用于生成预测。通过让用户检查预测背后的概念，并探索不同概念配置下的预测变化，CBMs已成为支持人机协作的重要方法。然而，关于其作为决策支持系统实际有效性的用户研究仍有限。我们进行了两项大规模用户研究（总参与者705人，观察6959次），评估基于概念的解释及用户对模型概念的干预如何影响两个不同二分类任务中的人机团队表现。结果表明，CBMs尤其是其交互组件，可在特定条件下提升人机团队准确率，优于未经辅助的人类表现或使用不可解释AI支持的表现。这些优势仅在任务被认为较难、概念易于识别且用户积极互动时显现。此外，概念检测不准确会削弱用户对模型的信任。本研究为CBMs作为有效决策支持工具的部署提供了实用指导。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。