Output Supervision Can Obfuscate the Chain of Thought

MATS 学员:

Luke Marks, Jacob Drori

作者:

Jacob Drori, Luke Marks, Bryce Woodworth, Alex Cloud, Alexander Matt Turner

引用次数

4 Citations

摘要:

OpenAI (2025) showed that training against a chain of thought (CoT) monitor can cause obfuscated CoTs, which contain bad behavior the monitor cannot detect. They proposed to keep CoTs monitorable by training only against output monitors that do not have access to CoT. We show that such training can still cause obfuscated CoTs via two mechanisms. First, when a model is trained to produce a safe-looking output, that model may generalize to making its CoTs look safe. Second, since later tokens are conditioned on earlier ones, safe-looking CoTs may increase the likelihood of safe outputs, causing safe-looking CoTs to be reinforced. We introduce two mitigations to address these two issues, which achieve a Pareto improvement in terms of monitorability and task performance compared to regular training.

近期研究

非大国冲突与 AI 风险

作者:

Kristina Kempkey

日期:

八月 26, 2026

引用次数:

合成角色预训练:从第一个 token 开始对齐

作者:

Julian Minder

日期:

八月 13, 2026

引用次数:

常见问题

什么是 MATS 项目?
项目持续多久?