RLHF
[/ɑːr el eɪtʃ ef/]
nounAI & Technology#ai#training#alignment#human-feedback0 views1 definitions
Definitions
Machine-assisted language draft. Human review still needed.
1
0
Automatischer Uebersetzungsentwurf (German) for "RLHF": Reinforcement Learning from Human Feedback — a training technique used to align language models with human preferences. Human raters compare model outputs and choose the better response; these preferences train a reward model which then guides further fine-tuning via reinforcement learning.
“Beispielentwurf: RLHF is the key step that turns a raw language model into a helpful, harmless assistant.”
by @dictionary_auto_translate1.1.1970