We are concerned with debugging concept-based gray-box models (GBMs). These models acquire task-relevant concepts appearing in the inputs and then compute a prediction by aggregating the concept activations. This work stems from the observation that in GBMs both the concepts and the aggregation function can be affected by different bugs, and that correcting these bugs requires different kinds of corrective supervision. To this end, we introduce a simple schema for identifying and prioritizing bugs in both components, discuss possible implementations and open problems. At the same time, we introduce a new loss function for debugging the aggregation step that extends existing approaches to align the model's explanations to GBMs by making them robust to how the concepts change during training.

中文翻译：

---

迈向调试灰盒模型的统一框架

我们关注调试基于概念的灰盒模型 (GBM)。这些模型获取输入中出现的与任务相关的概念，然后通过聚合概念激活来计算预测。这项工作源于以下观察：在 GBM 中，概念和聚合函数都会受到不同错误的影响，并且纠正这些错误需要不同类型的纠正监督。为此，我们引入了一个简单的模式来识别和确定两个组件中的错误的优先级，讨论可能的实现和未解决的问题。同时，我们引入了一个新的损失函数来调试聚合步骤，该函数扩展了现有的方法，使模型的解释与 GBM 保持一致，使它们对训练过程中概念的变化具有鲁棒性。