thunlp/PromptPapers

• highreadme#1

  Clarify the repo's primary purpose in the README's opening paragraph

  Why:

  CURRENT

  We have released an open-source prompt-learning toolkit, check out **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!

  COPY-PASTE FIX

  Copy

  This repository is a curated, must-read collection of papers on prompt-based tuning for pre-trained language models, maintained by Ning Ding and Shengding Hu. We strongly encourage researchers to make pull requests to update paper information! (See [contributing details](#contribution))
  
  We also have an open-source prompt-learning toolkit, check out **OpenPrompt!** 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!

  OpenDoneDismiss
• highlicense#2

  Add a LICENSE file to the repository

  Why:

  COPY-PASTE FIX

  Copy

  Create a `LICENSE` file in the root directory with the content of the Creative Commons Attribution 4.0 International (CC-BY-4.0) license.

  OpenDoneDismiss
• mediumtopics#3

  Update repository topics for accuracy and specificity

  Why:

  CURRENT

  ai, bert, machine-learning, nlp, pre-trained-language-models, prompt, prompt-based, prompt-learning, prompt-toolkit

  COPY-PASTE FIX

  Copy

  ai, bert, machine-learning, nlp, pre-trained-language-models, prompt, prompt-based, prompt-learning, prompt-engineering, paper-list, research-papers

  OpenDoneDismiss

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• CATEGORY QUERY

  What are the essential research papers for understanding prompt-based tuning in pre-trained language models?

  you: not recommended
  AI recommended (in order):

  1. GPT-3
  2. T5

  AI recommended 2 alternatives but never named thunlp/PromptPapers. This is the gap to close.

  Show full AI answer
• CATEGORY QUERY

  Where can I find a curated collection of significant works on prompt engineering for large language models?

  you: not recommended
  AI recommended (in order):

  1. Awesome-Prompt-Engineering
  2. Prompt Engineering Guide
  3. Learn Prompting
  4. Papers With Code
  5. arXiv
  6. Hugging Face

  AI recommended 6 alternatives but never named thunlp/PromptPapers. This is the gap to close.

  Show full AI answer

• Metadata completeness

  warn

  Suggestion:

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of thunlp/PromptPapers?

  pass
  ✓AI named thunlp/PromptPapers explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• If a team adopts thunlp/PromptPapers in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI named thunlp/PromptPapers explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• In one sentence, what problem does the repo thunlp/PromptPapers solve, and who is the primary audience?

  pass
  ✓AI named thunlp/PromptPapers explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?