#77 · Primary category： Prompt Engineering Tools
autoprompt
AutoPrompt: Automatic Prompt Construction for Masked Language Models.
Project last updated：07/17/26
GitHub Stars
641
Forks
86
Contributors
9
License
Apache-2.0
Why we included this project
AutoPrompt is the reference implementation of the method described in the EMNLP 2020 paper of the same name. Rather than hand-writing templates, it uses a gradient-guided search to learn trigger tokens for a task and then fills a [MASK] slot to make predictions. The repo includes runnable scripts for sentiment analysis, natural language inference, fact retrieval, and relation extraction, with command-line examples and label-token selection utilities. It is research code, not a maintained library: you will need to create a conda environment, pull datasets from a Google Drive link, and hook up the LAMA evaluation harness yourself. For teams reproducing published results or exploring prompt-based few-shot methods, it is a solid place to see how automatic prompt construction actually works.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
awesome-nano-banana-pro-prompts
🍌 World's largest Nano Banana Pro prompt library — 10,000+ curated prompts with preview images, 16 languages. Google Gemini AI image generation. Free & open source.
prompt-master
A Claude skill that writes the accurate prompts for any AI tool. Zero tokens or credits wasted. Full context and memory retention
chatgpt_system_prompt
A collection of GPT system prompts and various prompt injection/leaking knowledge.
awesome-nanobanana-pro
🚀 An awesome list of curated Nano Banana pro prompts and examples. Your go-to resource for mastering prompt engineering and exploring the creative potential of the Nano banana pro(Nano banana 2) AI image model.
awesome-gpt-image-2
🚀 World's largest GPT Image 2 prompt library, updated daily — 2000+ curated prompts with preview images, 16 languages. OpenAI's next-gen image model with pixel-perfect text rendering, cross-image consistency, and commercial-grade illustration. Free & open source.