csinva/tree-prompt
Tree prompting: easy-to-use scikit-learn interface for improved prompting.
Tree Prompting helps you classify text with better accuracy and efficiency without needing to fine-tune large language models. You provide a dataset of text examples and their correct classifications, along with a list of potential prompts. It then outputs a decision tree that uses these prompts to make more accurate predictions on new text, outperforming individual prompts.
No commits in the last 6 months.
Use this if you need to classify text data, like customer reviews or social media posts, and want to leverage the power of large language models without the high computational cost and complexity of fine-tuning.
Not ideal if your classification task requires extremely nuanced understanding beyond what pre-trained language models and simple prompts can achieve, or if you prefer a fully explainable, non-LLM based solution.
Stars
42
Forks
4
Language
Jupyter Notebook
License
—
Category
Last pushed
Oct 24, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/csinva/tree-prompt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
linshenkx/prompt-optimizer
一款提示词优化器，助力于编写高质量的提示词
Undertone0809/promptulate
🚀Lightweight Large language model automation and Autonomous Language Agents development...
CTLab-ITMO/CoolPrompt
Automatic Prompt Optimization Framework
microsoft/sammo
A library for prompt engineering and optimization (SAMMO = Structure-aware Multi-Objective...
Eladlev/AutoPrompt
A framework for prompt tuning using Intent-based Prompt Calibration