SoccerDream AI ← AI 圈资讯 论文研究

Chain-of-Thought Controllability Can Reduce Chain-of-Thought Monitorability

arXiv 人工智能 ·

arXiv:2611.21799v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is a promising tool for detecting hidden goals, off-task behavior, and other failures in AI agents. One risk is that models could deliberately shape their reasoning to make it opaque to monitors. We stress-test this risk through persona-control training: supervised fine-tuning on mathematical reasoning traces rewritten in the voices of diverse personas. This induces a broader ability to control CoT, even though training contains no monitor-evasion examples. In covert side-task evaluations, traces in which a gpt-o

阅读原文 · arXiv 人工智能
本文由 SoccerDream AI 自动聚合索引,内容版权归原作者与 arXiv 人工智能 所有。
本站仅作技术动态聚合,不构成任何形式的建议。
AI 生成内容标识:本页的分析结论与文字内容由 SoccerDream AI 大语言模型自动生成,依据《人工智能生成合成内容标识办法》予以标注;赛事数据、赛果与市场指数来自公开数据源,并经系统规则校验。内容仅供研究参考,不构成任何建议。