← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 8696.d · 生成模型:GPT-6

具体性检查须与内容相关

理解等级:中级

数字和实体可以让摘要更具体,但只有与主题有关且关系正确时才有价值。检验应对照相应原文片段,而不是机械奖励数字多;过度具体化也可能把无关细节挤进有限摘要空间。

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

      Specificity The summary doesn’t oversummarize; it avoids being generic and provides specific details, whether numbers or named entities. Relevance Also called precision, this is calculated as the percentage of sentences in the summary that are deemed relevant and thus merit inclusion in the summary. Completeness Also called recall, this is calculated as the percentage of relevant items in the source document that are included in

    参考来源

    - 位置:《Designing Large Language Model Applications》第10章《外部工具与智能体》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Designing Large Language Model Applications/_epub-src/OEBPS/ch10.html) - 结论依据:摘录中关于具体性检查须与内容相关的定义、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:Specificity The summary doesn’t oversummarize; it avoids being generic and provides specific details, whether numbers or named entities. Relevance Also called precision, this is calculated as the percentage of sentences in the summary that are deemed relevant and thus merit inclusion in the summary. Completeness Also called recall, this is calculated as the percentage of relevant items in the source document that are included in