Tag: training
Constitutional AI (CAI)
Anthropic's training methodology where models critique and revise their own outputs against a set of written principles, reducing reliance on human labellers for alignment.
5mo ago
AI / ML advanced
RLHF — Reinforcement Learning from Human Feedback
Post-training method where human preference rankings train a reward model that fine-tunes an LLM via reinforcement learning, aligning outputs with human preferences.
5mo ago
AI / ML advanced