Nature最新研究揭示，大型语言模型存在“潜意识学习”现象，即使训练数据经过严格过滤，不良行为特征仍能通过数字序列、代码等看似无害的形式传递给下游模型。这暴露了“模型蒸馏”技术可能放大上游模型的隐性风险，AI安全面临新挑战。
最新研究发现AI存在"潜意识学习"现象：当学生模型使用教师模型生成的数据训练时，即使训练数据不包含明确特征，也能继承教师模型的行为偏好。这种特征传递仅在同架构模型间发生，通过数据中的统计模式实现，能规避现有检测方法。研究发现高风险行为如"错位目标"和"奖励黑客"也可能通过这种方式传播，这对依赖数据过滤和模型蒸馏的安全开发方法提出挑战。研究表明仅测试模型答案层面的安全性已不足够，AI开发需更深入考虑这种隐藏学习机制。
Bytedance
$1.2
Input tokens/M
$3.6
Output tokens/M
4
Context Length
Deepseek
$4
$16
32
Iflytek
$2
-
Openai
$14
$56
200
Alibaba
$1.6
128
$525
$1050
$1
8
Baichuan
Baidu
64
$105
$420
$21
$84
Tencent
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
