Saltar al contenido
onsuggest
Iniciar sesión
Artículo en

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

Fuente: 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

¿Qué es Fun toy result: a subliminal-learning effect via on-policy distillation?

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

¿Cómo puedo acceder o experimentarlo?

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

¿De dónde proviene este contenido?

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

Atajos de teclado

Descubrimiento anterior
←P
Siguiente descubrimiento
→N
Me gusta
L
No es para mí
X
Guardar
S
Mostrar esta ayuda
?
Cerrar
Esc

Los atajos funcionan en la página de descubrimientos.