← Jargon

Jargonmachine learning· 17 claims· 8 episodes

reinforcement learning from human feedback (RLHF)

A training approach where a pre-trained model is fine-tuned using reward signals generated by human evaluators who judge the quality of model outputs, guiding the model toward desired behavior

As defined in The Mastermind Behind GPT-4 and the Future of AI | Ilya Sutskever


Other definitions

Where it comes up · 8