Skip to content
onsuggest
Log in
Article en

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

Source: 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

Open the original Discover more

Frequently Asked Questions

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

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

How can I access or experience this?

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

Where does this content come from?

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

All Culture & ideas discoveries →

Keyboard shortcuts

Previous discovery
←P
Next discovery
→N
Like
L
Not for me
X
Save
S
Show this help
?
Close
Esc

Shortcuts work on the discovery page.