mlsanityData to 7 Oct 2026

Do Prompts Solve NLP Tasks Using Natural Language?

arXiv 2203.00902 ↗First posted 2 Mar 2022cs.CLcited by 5

Not on the map. Why?

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 13 of its 21 references that are in the map. First posted on arXiv 2 Mar 2022.

Builds on

13 of 21 references.

References · 13

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2019Language Models as Knowledge Bases?cited by 1,922
  4. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  5. 2019How Can We Know What Language Models Know?cited by 953
  6. 2018Neural Network Acceptability Judgmentscited by 952
  7. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
  8. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 668
  9. 2021Structured Prediction as Translation between Augmented Natural Languagescited by 183
  10. 2021Template-Based Named Entity Recognition Using BARTcited by 153
  11. 2021Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Modelscited by 139
  12. 2020Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classificationcited by 98
1 more
  1. 2021Dialogue State Tracking with a Language Model using Schema-Driven Promptingcited by 94

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 0; 2024: 1; 2025: 2.

5 papers.

  1. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 886
  2. 2022Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learningcited by 36
  3. 2024Deconstructing In-Context Learning: Understanding Prompts via Corruptioncited by 4
  4. 2025Schema for In-Context Learningcited by 4
  5. 2025Retrieval-augmented Prompt Learning for Pre-trained Foundation Modelscited by 0