The reviewed record of science sign in
Pith

arxiv: 2203.00902 · v1 · pith:6RUA36LD · submitted 2022-03-02 · cs.CL

Do Prompts Solve NLP Tasks Using Natural Language?

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:6RUA36LDrecord.jsonopen to challenge →

classification cs.CL
keywords promptseffectivelanguagelargeschematasksthreetypes
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.