Generative AI
  • 📝Outline
  • 🧐Variational Autoencoder (VAE)
  • 🤓Diffusion Model
    • Diffusion Model
    • Latent Diffusion Model
  • 😎Transformer
    • Attention
    • Transformer
    • Switch Transformer
  • 🥸LLM
    • Introduction
    • Fine-tuning LLMs
    • Reinforcement Learning from Human Feedback (RLHF)
    • LLM-powered applications
  • 🤩Multi-modal Foundation Model
    • CLIP
Powered by GitBook
On this page
  1. LLM

Reinforcement Learning from Human Feedback (RLHF)

In RLHF, human labelers score a dataset of completions by the original model based on alignment criteria like helpfulness, harmlessness, and honesty. This dataset is used to train the reward model that scores the model completions during the RLHF process.

PreviousFine-tuning LLMsNextLLM-powered applications

Last updated 1 year ago

🥸