Presents the NATURAL INSTRUCTIONS meta-dataset and shows generative pre-trained language models achieve 19% better generalization to unseen tasks when using task instructions.
arXiv preprint arXiv:2103.11955 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2representative citing papers
Atlas reaches over 42% accuracy on Natural Questions with only 64 examples, outperforming a 540B-parameter model by 3% with 50x fewer parameters.
citing papers explorer
-
Cross-Task Generalization via Natural Language Crowdsourcing Instructions
Presents the NATURAL INSTRUCTIONS meta-dataset and shows generative pre-trained language models achieve 19% better generalization to unseen tasks when using task instructions.
-
Atlas: Few-shot Learning with Retrieval Augmented Language Models
Atlas reaches over 42% accuracy on Natural Questions with only 64 examples, outperforming a 540B-parameter model by 3% with 50x fewer parameters.