Model Based Rewards
topic on 1 show · 1 statements across 1 episodes
1 statements about Model Based Rewards, every show
Brown: RL training is shifting toward model-based LLM judges
“So it, like, feels like people are moving in the direction of model-based rewards, where you, either LLM is a judge where the judge sees the correct answer, or it has questions it's supposed to verify as properties of the response, just because that's much mor…”