MetaPrompting: Learning to Learn Better Prompts. (arXiv:2209.11486v2 [cs.CL] UPDATED)

Prompting method is regarded as one of the crucial progress for few-shot
nature language processing. Recent research on prompting moves from discrete
tokens based ``hard prompts'' to continuous ``soft prompts'', which employ
learnable vectors as pseudo prompt tokens and achieve better performance.
Though showing promising prospects, these soft-prompting methods are observed
to rely heavily on good initialization to take effect. Unfortunately, obtaining
a perfect initialization for soft prompts requires understanding of inner
language models working and elaborate design, which is …

arxiv learn