奖励模型Reward model
Reward model
解决什么问题What problem it solves
把「哪个回答更好」变成一个可打分的模型,为强化学习提供信号。Turn “which answer is better” into a scalar score that can drive reinforcement learning.
这是什么What it is
输入是一个问题加一个回答,输出是一个标量分数。
训练数据通常是人类或 AI 对多个回答的排序。
奖励模型不是最终产品,它是训练策略模型时的「裁判」。
Input is a question plus an answer; output is one scalar score.
Training data is usually human or AI rankings over multiple answers.
It is not the product model — it is the judge used while training the policy.
为什么需要知道Why it matters
奖励模型打分会直接决定模型学什么。裁判有偏见,模型就会学会讨好偏见。The reward model defines what the model learns to chase. A biased judge teaches the model to please the bias.
同域词条Terms in the same area
现在能做什么What you can do now
回到名词地图看第3站的其他 66 个词 →Back to the map: the other 66 terms in station 3 →
出处Sources
- Learning to summarize from human feedback(arXiv)Learning to summarize from human feedback (arXiv 2009.01325) ↗