microsoft/Evoke
Everything for the Paper: 'Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing'
This tool helps researchers and AI practitioners improve the quality of responses from large language models (LLMs). It takes an initial prompt and refines it automatically using a simulated reviewer-author feedback loop. The output is a more effective prompt that leads to better LLM performance on specific tasks.
No commits in the last 6 months.
Use this if you are an AI researcher or practitioner looking to automatically optimize prompts for your LLMs to achieve higher accuracy and more nuanced understanding of complex tasks.
Not ideal if you need a simple, manual way to create prompts or if you are not working with LLMs in a research or advanced application setting.
Stars
19
Forks
4
Language
—
License
MIT
Category
Last pushed
Dec 02, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/microsoft/Evoke"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
dottxt-ai/outlines
Structured Outputs
takashiishida/arxiv-to-prompt
Transform arXiv papers into a single LaTeX source that can be used as a prompt for asking LLMs...
microsoft/promptpex
Test Generation for Prompts
Spr-Aachen/LLM-PromptMaster
A simple LLM-Powered chatbot software.
AI-secure/aug-pe
[ICML 2024 Spotlight] Differentially Private Synthetic Data via Foundation Model APIs 2: Text