Lewis, Mike

Noisy Channel Language Model Prompting for Few-Shot Text Classification

2021 · arXiv (Cornell University)

We introduce a noisy channel approach for language model prompting in few-shot text classification. Instead of computing the likelihood of the label given the input (referred as direct models), channel models compute the conditional probability …

MetaICL: Learning to Learn In Context

2021 · arXiv (Cornell University)

We introduce MetaICL (Meta-training for In-Context Learning), a new meta-training framework for few-shot learning where a pretrained language model is tuned to do in-context learning on a large set of training tasks. This meta-training enables …