vicgalle/awesome-rlaif

A curated and updated list of relevant articles and repositories on Reinforcement Learning from AI Feedback (RLAIF)

21
/ 100
Experimental

This list helps AI researchers and practitioners stay current with the rapidly evolving field of Reinforcement Learning from AI Feedback (RLAIF). It provides a curated collection of research articles and repositories focusing on using AI to optimize large language models (LLMs) without human intervention, particularly through self-critique loops. If you are developing or studying advanced LLMs and want to explore methods for automated alignment and improvement, this resource is designed for you.

No commits in the last 6 months.

Use this if you are researching or developing advanced large language models and want to discover methods for aligning and improving them using AI-generated feedback rather than human preferences.

Not ideal if you are looking for general resources on traditional Reinforcement Learning from Human Feedback (RLHF) or are not involved in advanced LLM alignment research.

AI Alignment Large Language Models Machine Learning Research AI Ethics Generative AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

12

Forks

Language

License

Apache-2.0

Last pushed

Jan 24, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/vicgalle/awesome-rlaif"

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