用图形化方式设计可解释的AI模型，一眼看懂结构并直接转成代码。
Graphical Design of Interpretable Architectures
- 基于彭罗斯张量图设计新符号系统，直观呈现模型全局结构。
- 可将模型结构直接映射为33行PyTorch einsum代码，保证可复现。
- 适用于需要透明度的前沿模型如Steerling-8B，适合研究可解释性者。
设计、实现和比较可解释架构需要一种形式化语言来表达。现有表示方法存在缺陷：符号方程无法提供整体视图；概率图模型和流程图无法描述实际张量操作，隐藏关键洞察且限制可复现性。为此，我们引入一种基于彭罗斯张量记号的图形化表示法，既能提供全局视图，又能与PyTorch einsum代码一一对应。我们首先用该记号描述了构造上可解释的架构，包括概念瓶颈、稀疏探针、原型网络、神经加性模型和线性模型混合。接着，我们绘制了前沿可解释语言模型Steerling-8B的关键组件图示，揭示其为残差结构，给出每一步操作的几何解释，并生成33行可运行的PyTorch代码。
原文摘要 · Abstract (English)
Designing, implementing, and comparing interpretable architectures requires a formal language to represent them. The most common representations fall short in one of two ways. Symbolic equations give no global view of an architecture at a glance. Probabilistic graphical models and flowcharts do not describe actual tensor manipulations, thus hiding key insights and limiting reproducibility. To close this gap, we introduce a graphical notation for designing interpretable AI architectures, adapted from Penrose tensor notation. This graphical notation gives a global view of an architecture and maps one to one onto PyTorch einsum code. We first use this notation to describe architectures that are interpretable by construction, including concept bottlenecks, sparse probes, prototype networks, neural additive models, and mixtures of linear models. We then diagram the key architectural components of Steerling-8B, a frontier interpretable language model. The diagram yields global insights into the architecture (e.g., showing that Steerling is a residual model), a geometric interpretation of each individual operation, and a direct translation into 33 lines of PyTorch code.
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。