创建

登录 ReadmeX

或

了解我们如何处理你的信息: 隐私政策

ReadmeX

陪你读懂 AI 动态

今天,想先了解什么?

选一份动态总结,或直接聊聊你的问题。

社区和关注动态总结只属于你自己。

资讯

OpenAI研究思维链可监控性的影响因素

AI 总结

OpenAI Alignment研究人员考察了预训练、架构、强化学习和模型生成数据如何影响模型生命周期中的思维链可监控性。研究显示,基础模型困惑度下降和强化学习扩展与更强的无思维链能力及思维链可控性相关,架构与监督方式也会影响这些代理指标。研究人员同时指出,这些评估存在噪声,且只能不完美地代理监控规避能力。

深度见解

该研究显示,随着训练选择提升模型能力,依赖可见思维链进行可扩展监督会变得更困难,为前沿AI系统监控研究提供了直接依据。

What affects chain-of-thought monitorability across the model lifecycle?

How pretraining, architecture, reinforcement learning, and model-generated data affect chain-of-thought (CoT) monitorability.

November 10, 2026 Jeffrey G. Wang*, Aiden Low*, Zora Che*, Holden Mui*, Harshit Sikchi* Yong Zheng-Xin, Tomek Korbak❦, Bill Stavroulakis, Alex Barron, Shibani Santurkar, Kristian Georgiev Micah Carroll†, Ben Sokolowsky†, Katherine Lee†, Jakub Pachocki† * Equal contribution · ❦ Work done while at OpenAI · † Equal advising

Summary

We studied how pretraining, architecture, reinforcement learning, and model-generated data shape two proxies of CoT monitorability: no-CoT capability and CoT controllability.

Lower base-model perplexity and some architectural changes improve no-CoT reasoning, while RL and model-generated data can increase CoT controllability. These are imperfect proxies for monitorability, but together they indicate that models will become harder to monitor through their CoT as we scale toward more intelligent systems.

#OpenAI#GPT-6 Astra#OpenAI Alignment

原文约 20 分钟读完阅读原文
群聊

还没有评论,来说说你的看法。