Tag
Redwood Research 论文提出「蒸馏双困」框架，介绍两种利用蒸馏实现 AI 安全的方法：DFI 将失准模型的隐藏行为转移到更弱的学生模型以获取其失准证据，DFC 则通过免疫提示和少例多轮训练在保留能力的同时抑制失准的隐性迁移。
The paper introduces an algorithm allowing unfaithful LLM providers to artificially inflate reasoning paths for overcharging while evading detection, validated through experiments with models like Llama and Qwen.