Prompt-based

Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections
Prompt-Learning for Fine-Grained Entity Typing
Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners
Finetuned Language Models Are Zero-shot Learners
NSP-BERT: A Prompt-based Zero-Shot Learner Through an Original Pre-training Task —— Next Sentence Prediction
PPT: Pre-trained Prompt Tuning for Few-shot Learning