← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6517.e · 生成模型:GPT-6

裁判评分需要具体量规

理解等级:中级

模型裁判应收到任务、候选及明确的评分标准,必要时提供可靠参考。量规把评分对象具体化,但参考答案与量规仍可能有错误或漏项;一个示例被打高分不能证明裁判适用于整个任务集。

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

      pre-defined grading rubric (i.e., an evaluation guide) to compare an LLM's response to a reference response and judge the response quality based on a pre-defined rubric, as illustrated in figure F.6.

    参考来源

    - 位置:《Build a Reasoning Model (From Scratch)》第10章《附录F 常见模型评估方法》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Build a Reasoning Model (From Scratch)/_epub-src/OEBPS/Text/appendix-f.html) - 结论依据:摘录中关于裁判评分需要具体量规的定义、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:pre-defined grading rubric (i.e., an evaluation guide) to compare an LLM's response to a reference response and judge the response quality based on a pre-defined rubric, as illustrated in figure F.6.