ICLR
|
2022

Multitask prompted training enables zero-shot task generalization

V. Sanh, et al

Abstract

This paper showcases how using a data-centric approach to generate high-quality training data at massive scale to improve the zero-shot abilities of that model.

Share this article
Coming Fall 2026
ImageImage
A one-day, invite-only summit providing a first look at the benchmarks and research that will shape the frontier. Sign up for updates.