hyintell/awesome-refreshing-llms

EMNLP'23 survey: a curation of awesome papers and resources on refreshing large language models (LLMs) without expensive retraining.

37
/ 100
Emerging

This is a curated collection of research papers and resources focused on how to keep large language models (LLMs) current with new information without the massive cost and effort of fully retraining them. It provides a comprehensive overview of methods to update an LLM's knowledge, whether by directly altering its internal parameters or by integrating external, up-to-date information. Data scientists, machine learning engineers, and researchers working with LLMs would find this valuable for maintaining accurate and timely AI applications.

136 stars. No commits in the last 6 months.

Use this if you are a researcher or practitioner exploring techniques to update the knowledge of deployed large language models efficiently, without performing expensive full retraining.

Not ideal if you are looking for an out-of-the-box software tool to directly apply knowledge updates to an LLM without understanding the underlying research.

Large Language Models Machine Learning Engineering Model Updating AI Research Knowledge Management
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

136

Forks

11

Language

License

MIT

Last pushed

Dec 12, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/hyintell/awesome-refreshing-llms"

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