Self-supervised Meta-Prompt Learning with Meta-Gradient Regularization for Few-shot Generalization. (arXiv:2303.12314v4 [cs.CL] UPDATED) Show more
http://arxiv.org/abs/2303.12314 #arXiv #NLProc
QOTO: Question Others to Teach Ourselves An inclusive, Academic Freedom, instance All cultures welcome. Hate speech and harassment strictly forbidden.