跳到内容
onsuggest
登录
文章 en

Fun toy result: a subliminal-learning effect via on-policy distillation

来源: LessWrong ·

In the standard subliminal learning setup, a teacher model with a preference generates data according to its policy, and then the student is trained on those data. I wondered if it was necessary for the teacher model to actually get to control the produced tokens, so I instead let a no-prompt "teacher" model produce the sequences to be trained on. Then I trained the student against a subliminal-learning-prompted teacher model's logits on those sequences. (Since an unmodified "teacher" is identical to the student model, this is equivalent to just doing on-policy distillation from the prompted t

什么是 Fun toy result: a subliminal-learning effect via on-policy distillation?

Fun toy result: a subliminal-learning effect via on-policy distillation is a 文章 discovery curated from LessWrong. In the standard subliminal learning setup, a teacher model with a preference generates data according to its policy, and then the student is trained on those data. I wondered if it

如何访问或体验此内容?

You can experience this content directly on its original host (LessWrong) by clicking the "Open Original" button.

此内容来源于哪里?

Curated from LessWrong by the OnSuggest team to surface the most interesting and serendipitous content on the web.

键盘快捷键

上一条发现
←P
下一条发现
→N
喜欢
L
不适合我
X
保存
S
显示此帮助
?
关闭
Esc

快捷键在发现页面上有效。