返回首页
arXiv AI··论文与技术

An Operationalization of Opaque Serial Depth

中文摘要

本文提出“不透明串行深度”来衡量 AI 模型中不可见的串行认知,通过量化绕过解释性标记的计算路径,评估思维链的可监控性。

English Summary

This paper introduces "opaque serial depth" to measure unobservable serial computation in AI, quantifying how much reasoning bypasses interpretable tokens, potentially reducing Chain-of-thought monitorability.

原文节选

arXiv:2611.17495v1 Announce Type: new Abstract: Chain-of-thought (CoT) is currently a valuable tool for overseeing AI models, but some architectural shifts could significantly reduce CoT monitorability. We operationalize a measure that serves as a proxy for the amount of unverbalized serial cognition a model can perform, as a specific instantiation of the notion of opaque serial depth: roughly, the length of the longest path through a model's computation that does not pass through an interpretable bottleneck. Our main contribution is a particular standard for what counts as such a bottleneck. We define natural-language-rooted (NL-rooted) nodes as nodes that were initialized from a pre-training prior to produce human-understandable outputs, whose output space has not been expanded beyond that prior, and whose outputs the model has not been modified to interpret as a different type of data. By construction, the resulting measure, NLS depth, can be adjudicated before training from an architecture, training recipe, and deployment configuration alone, and is insensitive to ordinary post-training such as prompting, distillation, and RL. We find that, across open-weight models, NLS depth …