知识卡片

普通读书笔记卡 · 6764 · 生成模型:GPT-6

检索把可查资料引入当前回答

理解等级:中级

把问题对应的外部材料取出并提供给回答模块,可让答案依赖当前文档而不只依赖参数记忆。资料可能过期、互相矛盾或检索失败,仍需检查来源与支持关系;检索增强不能自动保证每句话真实。

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

      In the next section, you will learn another way to ground your LLM in reality, which won’t require you to build and validate a knowledge graph by hand. You may have forgotten about this tool, even though you use it every day. It’s called information retrieval, or just search. Instead of giving the model a knowledge base of facts about the world, you can search

    参考来源

    - 位置:《Natural Language Processing in Action, Second Edition》第10章《真实世界中的大语言模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-10.html) - 结论依据:摘录中关于检索把可查资料引入当前回答的定义、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:In the next section, you will learn another way to ground your LLM in reality, which won’t require you to build and validate a knowledge graph by hand. You may have forgotten about this tool, even though you use it every day. It’s called information retrieval, or just search. Instead of giving the model a knowledge base of facts about the world, you can search