Practice
Learn
← Quit
0 / 0 correct
LLMs & AI
Hard
1 of 40
How does RLHF work at a high level?
A
Humans compare responses; a reward model learns their preferences; the LLM is optimized (e.g. with PPO) to maximize reward while staying close to the original model
B
It removes harmful tokens from the vocabulary
C
The model rewards itself with no human data
D
Humans write all training text