Anthropic这篇论文把思维链和steering向量的工作机制讲透了，告诉你什么时候推理是真起作用，什么时候只是马后炮。搞可解释和推理的都该看看。
Anthropic发布arXiv论文（2607.15495），提出LLM中的全局工作空间假说。该假说认为模型能用语言表达的表征像一个带宽受限的共享通道，将少量特征广播到网络其余部分。这为chain-of-thought和steering向量提供了机械论解释：当verbalized reasoning（语言化推理）真正承载负载时，它如何影响后续输出；而当它只是事后叙述时又是什么机制。论文基于Anthropic的J-space研究，将推理过程与神经网络的内部表征联系。
// Global Workspace in LLMs // arXiv paper for the popular J-space work from Anthropic. (bookmark ...
// Global Workspace in LLMs // arXiv paper for the popular J-space work from Anthropic. (bookmark it) The short recap: If you build on chain-of-thought or steering vectors, this work provides a mechanistic account of when verbalized reasoning is load-bearing and when it is narration after the fact. The representations a model can put into words behave like a shared global workspace, a bandwidth-limited channel that broadcasts a small set of features to the rest of the network and steers what it does next. Paper: arxiv.org/abs/2607.15495 Learn to build effective AI agents in our academy: academy.dair.ai 💬 10 🔄 3 ❤️ 11 👀 2698 📊 13 ⚡
- arXiv cs.LG07-20 17:07原文