OpenPrompt: An Open-source Framework for Prompt-learning

By Ning Ding, Shengding Hu, Weilin Zhao, Yulin Chen, Zhiyuan Liu, Haitao Zheng, Maosong Sun. Annual Meeting of the Association for Computational Linguistics, 2021

344 citations recorded by the source corpus.

Prompt-learning has become a new paradigm in modern natural language processing, which directly adapts pre-trained language models (PLMs) to cloze-style prediction, autoregressive modeling, or sequence to sequence generation, resulting in promising performances on various tasks. However, no standard implementation framework of prompt-learning is proposed yet, and most existing prompt- learning codebases, often unregulated, only provide limited implementations for specific scenarios. Since there are many details such as templating strategy, initializing strategy, verbalizing strategy, etc., that need to be considered in prompt-learning, practitioners face impediments to quickly adapting the de-sired prompt learning methods to their applications. In this paper, we present Open- Prompt, a unified easy-to-use toolkit to conduct prompt-learning over PLMs. OpenPrompt is a research-friendly framework that is equipped with efficiency, modularity, and extendibility, and its combinability allows the freedom to combine different PLMs, task for- mats, and prompting modules in a unified paradigm. Users could expediently deploy prompt-learning frameworks and evaluate the generalization of them on different NLP tasks without constraints.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/614dd2ae6db71cd5b2a6069407d3e0705ab2c19c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Zhiyuan Liu
2. Maosong Sun
3. Xu Han
4. Shafiq R. Joty
5. Chengwei Qin
6. Ning Ding
7. Juan-Zi Li
8. Yejin Choi

In Computer Vision and Pattern Recognition

1. Zhiyuan Liu
2. Maosong Sun
3. Xu Han
4. Yejin Choi
5. Tom Goldstein
6. Shafiq R. Joty
7. Micah Goldblum
8. Lei Li

Citations in the corpus

• A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities (2022, background): “According to the location of the prompt, prompt learning can be divided into preix prompt [107, 108] and cloze-style prompt [87, 107, 109].”
• Chain of Explanation: New Prompting Method to Generate Quality Natural Language Explanation for Implicit Hate Speech (2022, background): “The potential of sequence-to-sequence (Seq2Seq) models and prompting methods has not been fully explored [4].”
• Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting (2023, background): “Another approach is to learn, optimize, and insert continuous representations of prompts and tasks as input to models (Qin & Eisner, 2021; Lester et al., 2021; Ding et al., 2022; Ilharco et al., 2023).”
• Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery (2023, background): “Zhang et al. (2021), Hu et al. (2022), and Li et al. (2022) achieve this goal by training large captioning models on image-text pairs.”
• Why Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts (2023, background): “In this paradigm, people without programming skills or NLP knowledge can nonetheless make NLP models generate desired interactions by crafting efective prompt strategies (e.g., natural language instructions, examples, and templates) [3, 15].”
• Is GPT-3 a Good Data Annotator? (2022, background): “Prompt-Learning Prompt-Learning, also known as Prompting, offers insight into what the future of NLP may look like (Lester et al., 2021; Liu et al., 2021c; Ding et al., 2021b).”
• AI literacy and its implications for prompt engineering strategies (2024, background): “As of now, most research on prompt engineering has been conducted from a technology-centric viewpoint (Ding et al., 2021; P. Liu et al., 2023).”
• Prompt-Learning for Fine-Grained Entity Typing (2021, methodology): “…PLMs like GPT (Rad-ford et al., 2018), BERT (Devlin et al., 2019), RoBERTa (Liu et al., 2019) and T5 (Raffel et al., 8.6% 5.5% 3.5% denotes the correct predictions, denotes the wrong predictions with correct coarse-grained types, and denotes the wrong predictions with wrong coarse-grained types.”
• Pre-trained Language Models Can be Fully Zero-Shot Learners (2022, methodology): “We implement our experiments based on an open-source toolkit OpenPrompt (Ding et al., 2021), which aims to conduct prompt learning easily.”
• Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification (2021, methodology): “Our experiments are based on OpenPrompt (Ding et al., 2021), which is an open-source toolkit to conduct prompt learning.”