1 result

for reward-model

• RLHF: train a critic from human rankings, then optimise against the critic
  Reinforcement learning from human feedback is the standard recipe for aligning a language model with preferences that are hard to write down as a loss function — the motivating case being responses th
  field/rlhf-and-alternatives · rlhf, alignment, dpo, training, llm, reward-model