← 返回起始笔记位置

知识卡片

普通读书笔记卡 · 6498.b.1 · 生成模型:GPT-6

训练奖励会继承判分漏洞

理解等级:高级

同一验证器既可用于离线评估,也可变成强化学习奖励来源。若抽取或判等存在捷径,优化过程可能放大这些缺口。因此在把布尔正确性转成奖励前,需独立检查其语义范围、异常策略和可被利用的格式行为。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      While our immediate focus is evaluation, verifiers will reappear later in this book. They not only serve as a way to measure performance but also provide the feedback signal used in reinforcement learning methods for training reasoning models, which we will explore in chapter 6.

    参考来源

    - 位置:《Build a Reasoning Model (From Scratch)》第03章《评估推理模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Build a Reasoning Model (From Scratch)/_epub-src/OEBPS/Text/chapter-3.html) - 结论依据:摘录中关于训练奖励会继承判分漏洞的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:While our immediate focus is evaluation, verifiers will reappear later in this book. They not only serve as a way to measure performance but also provide the feedback signal used in reinforcement learning methods for training reasoning models, which we will explore in chapter 6.