知识卡片
因果框架选择需显式记录
因果框架界定当前问题考虑哪些变量和背景条件。LLM可根据叙述或日志提出相关因素,但其省略的因素并不因此无关;应记录为何纳入、排除或作为隐藏量,防止把常见叙事模板误当DGP充分描述。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
- · 因果与大语言模型
原书出处 · 1 处
- · 查看原书依据
13.1.4 The causal frame problem and AI alignment Given a query of interest, we have to decide what variables are relevant to the problem. Philosoper and AI researcher Clark Glymour does a good job of describing the challenge behind this task: “Given an enormous amount of stuff, and some task to be done using some of the stuff, what is the relevant stuff for the
参考来源
- 位置:《Causal AI》第13章《因果与大语言模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-13.xhtml)
- 结论依据:摘录中关于因果框架选择需显式记录的定义、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:13.1.4 The causal frame problem and AI alignment Given a query of interest, we have to decide what variables are relevant to the problem. Philosoper and AI researcher Clark Glymour does a good job of describing the challenge behind this task: “Given an enormous amount of stuff, and some task to be done using some of the stuff, what is the relevant stuff for the