Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Must-read papers on prompt-based tuning for pre-trained language models.
| Date | Stars |
|---|---|
| 2026-07-24 | 4323 |
| 2026-07-25 | 4323 |
| 2026-07-28 | 4323 |
| 2026-07-30 | 4323 |
| 2026-07-31 | 4325 |
| 2026-08-06 | 4325 |
Today
— stars today
This week
+2 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.05%/day
# PromptPapers
  
We have released an open-source prompt-learning toolkit, check out **[OpenPrompt](https://github.com/thunlp/OpenPrompt)!**
We strongly encourage the researchers that want to promote their fantastic work to the community to make **pull request** to update their paper's information! (See [contributing details](#contribution))
Effective adaptation of pre-trained models could be probed from different perspectives. Prompt-learning more focuses on the organization of training procedure and the unification of different tasks, while delta tuning (parameter efficient methods) provides another direction from the specific optimization of pre-trained models. Check [DeltaPapers](https://github.com/thunlp/DeltaPapers)!
<!-- omit in toc -->
## Contents
Must-read papers on prompt-based tuning for pre-trained language models. The paper list is mainly mantained by [Ning Ding](https://github.com/ningding97) and [Shengding Hu](https://github.com/shengdinghu). Watch this repository for the latest updates!
- [PromptPapers](#promptpapers)
- [Introduction](#introduction)
- [Keywords Convention](#keywords-convention)
- [Papers](#papers)
- [Overview](#overview)
- [Pilot Work](#pilot-work)
- [Basics](#basics)
- [Analysis](#analysis)
- [Improvements](#improvements)
- [Specializations](#specializations)
- [Contribution](#contribution)
- [Other contributors](#other-contributors)
- [Contributing to this paper list](#contributing-to-this-paper-list)
## Introduction
This is a paper list about **prompt-based tuning** for large-scale pre-trained language models. Different from traditional fine-tuning that uses an explicit classifier, prompt-based tuning directly uses the pre-trained models to conduct the pre-training tasks for classification or regression.
### Keywords Convention
 The abbreviation of the work.
 The key features in terms of prompt learning used in the work.
 The mainly explored task of the work.
 The mainly explored property of prompt learning methods in the work.
## Papers
### Overview
This section contains the papers that overview the general trends in recent natural language processing with big (pretrained) models.
1. **OpenPrompt: An Open-source Framework for Prompt-learning.** Preprint.
*Ning Ding, Shengding Hu, Weilin Zhao, Yulin Chen, Zhiyuan Liu, Hai-Tao Zheng, Maoson Sun* [[pdf](https://arxiv.org/pdf/2111.01998.pdf)] [[project](https://github.com/thunlp/OpenPrompt)], 2021.11
2. **Pre-Trained Models: Past, Present and Future.** Preprint.
*Xu Han, Zhengyan Zhang, Ning Ding, Yuxian Gu, Xiao Liu, Yuqi Huo, Jiezhong Qiu, Yuan Yao, Ao Zhang, Liang Zhang, Wentao Han, Minlie Huang, Qin Jin, Yanyan Lan, Yang Liu, Zhiyuan Liu, Zhiwu Lu, Xipeng Qiu, Ruihua Song, Jie Tang, Ji-Rong Wen, Jinhui Yuan, Wayne Xin Zhao, Jun Zhu.* [[pdf](https://arxiv.org/abs/2106.07139)], 2021.6
3. **Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing.** Preprint.
*Liu, Pengfei, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig.* [[pdf](https://arxiv.org/abs/2107.13586)] [[project](http://pretrain.nlpedia.ai)], 2021.7
4. **Paradigm Shift in Natural Language Processing.** Machine Intelligence Research.
*Tianxiang Sun, Xiangyang Liu, Xipeng Qiu, Xuanjing Huang* [[pdf](https://arxiv.org/abs/2109.12575)] [[project](https://txsun1997.github.io/nlp-paradigm-shift/)], 2021.9
### Pilot Work
This section contains the pilot works that might contributes to the prevalence of prompt learning paradigm.
1. **Parameter-Excerpt of 38,787 characters
Read on GitHub
DingDing · @tsinghua
29
StingNing · Tsinghua University
14
muhtasham · stealth · United States
6
Eric
4
Shaw · Tsinghua University · China
4
Chenglei
2
Tianbao Xie · The University of Hong Kong · Hong Kong
2
Nihal Nayak · Harvard University · Morocco
2
Fábio Perez · Brazil
2
2
shizhediao · Thinking Machines Lab · United States
2
1
Tianxiang Sun · @analemmaai · China
1
kiko
1
Ganqu CUI · Tsinghua University · China
1
Lei Li · Zhejiang Univeristy, Tencent · China
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:646b727d7cfb3d33, topic:nlp, readme:natural language processing
matched fp:646b727d7cfb3d33, topic:prompt