本文へスキップ
onsuggest
ログイン
記事 en

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

情報源: 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

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

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

どのようにアクセスまたは体験できますか?

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

このコンテンツの提供元は?

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

キーボードショートカット

前の発見
←P
次の発見
→N
いいね
L
合わない
X
保存
S
このヘルプを表示
?
閉じる
Esc

ショートカットは発見ページで使えます。