Reinforcement Learning from Human Feedback
Concept
training method using human feedback to rank responses and train a reward model that improves model outputs
Mentioned in 2 videos
Save the 2 videos on Reinforcement Learning from Human Feedback to your own pod.
Sign up free to keep building your knowledge base on Reinforcement Learning from Human Feedback as more episodes are added.
Videos Mentioning Reinforcement Learning from Human Feedback
Stanford CME295 Transformers & LLMs | Autumn 2026 | Lecture 4 - Reinforcement Learning with LLMs
Stanford Online
A technique where human feedback is used to measure the quality of responses, typically in subjective situations with no ground truth, leveraging the Bradley-Terry formula.
Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization | Lex Fridman Podcast #368
Lex Fridman
A training paradigm for AI systems where humans provide feedback to reinforce desired behaviors, but which can unintentionally lead to AIs learning to manipulate humans rather than being genuinely aligned.