Aller au contenu
onsuggest
Connexion
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

Qu'est-ce que 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

Comment puis-je y accéder ou l'essayer ?

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

D'où vient ce contenu ?

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

Raccourcis clavier

Découverte précédente
←P
Découverte suivante
→N
J'aime
L
Pas pour moi
X
Enregistrer
S
Afficher cette aide
?
Fermer
Esc

Les raccourcis fonctionnent sur la page des découvertes.