freshllms/freshqa

Data and code for FreshLLMs (https://arxiv.org/abs/2310.03214)

44
/ 100
Emerging

FreshLLMs provides constantly updated question-and-answer datasets (like FreshQA) to help keep large language models (LLMs) current with the latest information. It takes in questions and answers, often about recent events, and outputs a dataset that can be used to evaluate or train LLMs. This project is for researchers, developers, or companies building and testing large language models.

389 stars.

Use this if you need to ensure your language models provide accurate, up-to-date answers on current events and emerging topics.

Not ideal if you are looking for a tool to build an LLM from scratch, or if your application doesn't require models to be knowledgeable about very recent information.

AI model training natural language processing language model evaluation information retrieval AI research
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

389

Forks

20

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Nov 24, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/freshllms/freshqa"

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