Think
LLM
Models
Capabilities
Use Cases
Benchmarks
Papers
Glossary
Search
/
Glossary
/
Reinforcement Learning from AI Feedback (RLAIF)
Reinforcement Learning from AI Feedback (RLAIF)
techniques
Training models using rewards generated by AI systems (like LLM judges) instead of human feedback.
Reinforcement Learning from AI Feedback (RLAIF) — Glossary — ThinkLLM