Concept-based interpretability methods offer a lens into the internals of
foundation models by decomposing their embeddings into high-level concepts.
These concept representations are most useful when they are compositional,
meaning that the individual concepts compose to explain the full sample. We
show that existing unsupervised concept extraction methods find concepts which
are not compositional. To automatically discover compositional concept
representations, we identify two salient properties of such representations,
and propose Compositional Concept Extraction (CCE) for finding concepts which
obey these properties. We evaluate CCE on five different datasets over image
and text data. Our evaluation shows that CCE finds more compositional concept
representations than baselines and yields better accuracy on four downstream
classification tasks. Code and data are available at
this https URL .

利用概念为基础的可解释性方法，通过将其嵌入分解为高级概念，提供了一种深入研究基础模型内部的透视角度。我们展示了现有的无监督概念抽取方法找到的概念并不是可组合的。为了自动发现可组合的概念表示，我们确定了这些表示的两个显著特性，并提出了用于找到符合这些特性的概念的可组合概念抽取算法 (CCE)。我们在图像和文本数据上评估了 CCE，并且结果表明 CCE 找到了更多可组合的概念表示，并在四个下游分类任务上取得了更好的准确率。代码和数据可在 https:// 此网址 获取。