di37/multiclass-news-classification-using-llms

This repository contains a project that focuses on evaluating the performance of different Language Models (LLMs) for multi-class news classification. The project aims to assess how well LLMs can classify news articles into five distinct categories: business, politics, sports, technology, and entertainment.

19
/ 100
Experimental

This project helps anyone who needs to automatically sort large volumes of news articles. By taking raw news article text, it categorizes them into topics like business, politics, sports, technology, and entertainment. This is most useful for media analysts, content curators, or market researchers.

No commits in the last 6 months.

Use this if you need to quickly and accurately sort news articles into predefined categories, especially when comparing the performance and resource usage of different large language models for this task.

Not ideal if your categorization needs are highly specialized beyond general news topics, or if you need to classify extremely short snippets of text where context is minimal.

news-analysis content-categorization media-monitoring information-organization text-analytics
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

18

Forks

1

Language

Jupyter Notebook

License

Last pushed

May 25, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/di37/multiclass-news-classification-using-llms"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.