jaehyun513/P2T
Official implementation of Tabular Transfer Learning via Prompting LLMs (COLM 2024).
This project helps data scientists and machine learning engineers apply knowledge from one tabular dataset to improve predictions on a new, related tabular dataset. It takes your existing tabular data and a new dataset, then uses large language models (LLMs) to generate better predictive models for the new data. This is useful for anyone working with structured data who needs to build accurate predictive models quickly, even with limited data.
No commits in the last 6 months.
Use this if you need to build a predictive model for a new dataset, but you have similar data from a past project that could help improve performance.
Not ideal if you primarily work with unstructured data like text or images, or if you don't have any related prior datasets to leverage.
Stars
13
Forks
—
Language
Jupyter Notebook
License
—
Category
Last pushed
Aug 06, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/jaehyun513/P2T"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
meta-prompting/meta-prompting
Official implementation of Meta Prompting for AI Systems (https://arxiv.org/abs/2311.11482)
auniquesun/Point-PRC
[NeurIPS 2024] Official implementation of the paper "Point-PRC: A Prompt Learning Based...
hemangjoshi37a/o1-meta-prompt
This project aims to emulate some of the advanced reasoning capabilities seen in models like...
slashrebootofficial/simulated-metacognition-in-open-source-llms
This repository archives artifacts (prompts, configs, logs, and scripts) from a series of...
RamonKaspar/MathPrompter
MathPrompter Implementation: This repository hosts an implementation based on the 'MathPrompter:...