Prompting a pretrained transformer can be a universal approximator

Despite the widespread adoption of prompting, prompt tuning and prefix-tuning of transformer models, our theoretical understanding of these fine-tuning methods remains limited. A key question is whether one can arbitrarily modify the behavior of a pretrained model by prompting or prefix-tuning it. F...

Descripció completa

Dades bibliogràfiques
Autors principals: Petrov, A, Torr, PHS, Bibi, A
Format: Conference item
Idioma:English
Publicat: PMLR 2024