知识卡片

普通读书笔记卡 · 6758.f · 生成模型:GPT-6

解释性需要与真实决策过程对应

理解等级:中级

自然语言理由可能只是事后生成,能说出解释不保证忠实描述内部决策。知识图谱或可查来源可提供审计材料,仍需验证边与证据;理解错误来源有助改进,但解释本身不自动消除偏见和误导。

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

      So which one of these pressing topics are you most concerned with? Are there some overlapping topics you can work on to both reduce the harm to humans now and prevent our extinction in the long run? Perhaps explainable AI should be at the top of your list of ways to help create ethical and safe AI. Explainable AI is the concept of an algorithm

    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:摘录中关于解释性需要与真实决策过程对应的定义、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:So which one of these pressing topics are you most concerned with? Are there some overlapping topics you can work on to both reduce the harm to humans now and prevent our extinction in the long run? Perhaps explainable AI should be at the top of your list of ways to help create ethical and safe AI. Explainable AI is the concept of an algorithm