MATS 学员:
Luke Marks, Jacob Drori
作者:
Jacob Drori, Luke Marks, Bryce Woodworth, Alex Cloud, Alexander Matt Turner
引用次数
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.
MATS 是一个独立的研究与教育项目,致力于连接新兴研究人员与 AI 对齐、治理和安全领域的导师。
每期 MATS 项目在加州伯克利进行,为期 12 周。部分学员可选择之后前往伦敦参加为期 6 至 12 个月的延伸项目。