Zum Inhalt springen
onsuggest
Anmelden
Artikel en

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

Quelle: 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

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

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

Wie kann ich darauf zugreifen oder es ausprobieren?

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

Woher stammt dieser Inhalt?

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

Tastaturkürzel

Vorherige Entdeckung
←P
Nächste Entdeckung
→N
Mögen
L
Nicht für mich
X
Speichern
S
Diese Hilfe anzeigen
?
Schließen
Esc

Die Kürzel funktionieren auf der Entdeckungsseite.