https://github.com/vishakhpk/creative-instructions
T0: Multitask Prompted Training Enables Zero-Shot Task Generalization
T5: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
InstructGPT: Training language models to follow instructions with human feedback
Emergent Abilities of Large Language Models
FLAN: Finetuned Language Models Are Zero-Shot Learners