Thanks to the advanced improvement of large pre-trained language models, prompt-based fine-tuning is shown to be effective on a variety of downstream tasks. Though many prompting methods have been investigated, it remains unknown which type of prompts are the most effective among three types of prompts (i.e., human-designed prompts, schema prompts and null prompts). In this work, we empirically compare the three types of prompts under both few-shot and fully-supervised settings. Our experimental results show that schema prompts are the most effective in general. Besides, the performance gaps tend to diminish when the scale of training data grows large.
@article{arxiv.2203.00902,
title = {Do Prompts Solve NLP Tasks Using Natural Language?},
author = {Sen Yang and Yunchen Zhang and Leyang Cui and Yue Zhang},
journal= {arXiv preprint arXiv:2203.00902},
year = {2022}
}