用概念电路解析ViT如何内化世界知识，实现可解释推理。
"World Knowledge" in the Weights: Reading Concept Circuits of Vision Transformers
- 通过跨层转换器提取稀疏可解释的概念图谱，捕捉层级间语义交互。
- 在Waterbird数据集上提升11.0%准确率，有效识别并消除模型捷径依赖。
- 适用于模型可解释性分析、对抗样本检测与不同视觉模型的结构对比。
视觉变压器（ViTs）在跨视觉领域表现出卓越泛化能力，但其内部如何表征世界结构仍不清晰。本文提出跨层转换器（CLTs），从ViTs中读取概念电路：节点代表稀疏可解释的概念，边表示层间概念交互。该方法提供两种互补视角：全局概念电路与输入无关，可直接从跨层权重中恢复，揭示模型中可复用的“世界知识”；实例概念电路依赖输入，用于追踪特定预测所激活的概念路径，支持细粒度解释。我们通过三方面验证其有效性：（1）自动发现模型中的虚假相关性，基于全局概念电路统计；（2）通过干预实例概念电路，引导模型做出正确预测，在Waterbird数据集上性能优于现有方法11.0%；（3）对比不同基础模型（如CLIP与DINO）的全局概念电路，揭示监督范式如何塑造表征结构。代码已开源。
原文摘要 · Abstract (English)
Vision transformers (ViTs) have achieved remarkable generalization across visual domains, yet little is known about how they internally represent the structure of the world. To address this gap, we use Cross-Layer Transcoders (CLTs) to read concept circuits from ViTs: directed graphs whose nodes correspond to sparse, interpretable concepts and edges capture concept interactions across layers. Our method yields two complementary views of model behavior. The global concept circuit is input-invariant and can be recovered directly from learned cross-layer weights, exposing the reusable "world knowledge" encoded in the model. The instance concept circuit is input-dependent and identifies the concepts and pathways actually used for a specific prediction, enabling faithful example-level explanations. We demonstrate the utility of concept circuits in three ways: (1) Automatic spurious correlation discovery: leveraging the statistics of our global concept circuits to identify shortcut dependencies within the model. (2) Spurious correlation removal: intervening on the instance concept circuit to steer the model towards correct predictions. Empirical results show that our method outperforms existing counterparts by 11.0% on the Waterbird dataset. (3) Model comparison: contrasting the global concept circuits of different foundation models (e.g., CLIP vs. DINO) to reveal how supervision paradigms shape representational structure. Our code is available at https://github.com/deep-real/VisionCLT
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。