# Do Prompts Solve NLP Tasks Using Natural Language?

arXiv: https://arxiv.org/abs/2203.00902 · HTML: https://mlsanity.com/paper/2203.00902/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 2 Mar 2022.

## Builds on (most cited first, 13 of 13)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://mlsanity.com/paper/2009.07118/) (2020)
- [Structured Prediction as Translation between Augmented Natural Languages](https://mlsanity.com/paper/2101.05779/) (2021)
- [Template-Based Named Entity Recognition Using BART](https://mlsanity.com/paper/2106.01760/) (2021)
- [Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models](https://mlsanity.com/paper/2106.13353/) (2021)
- [Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification](https://mlsanity.com/paper/2010.13641/) (2020)
- [Dialogue State Tracking with a Language Model using Schema-Driven Prompting](https://mlsanity.com/paper/2109.07506/) (2021)

## Built on by (most cited first, 5 of 5)

- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning](https://mlsanity.com/paper/2205.14704/) (2022)
- [Deconstructing In-Context Learning: Understanding Prompts via Corruption](https://mlsanity.com/paper/2404.02054/) (2024)
- [Schema for In-Context Learning](https://mlsanity.com/paper/2510.13905/) (2025)
- [Retrieval-augmented Prompt Learning for Pre-trained Foundation Models](https://mlsanity.com/paper/2512.20145/) (2025)

## Abstract (arXiv)

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.