知识卡片
答对术语不等于识别现实目标
模型能复述PN定义或写对一个符号查询,体现的是相关语言与理论知识;给特定现实人群估计PN则还需数据和识别假设。不能因模型答对形式化题就声称已知道现实反事实分布,也不能把任何定义题都要求现实干预数据。
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
Netflix question about probability of necessity correct. Indeed, the hallucinated answer would have been right if it merely stated the correct identifying assumptions. I believe future versions of GPT and similar models will likely get this question right on the first try.
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:摘录中关于答对术语不等于识别现实目标的定义、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:Netflix question about probability of necessity correct. Indeed, the hallucinated answer would have been right if it merely stated the correct identifying assumptions. I believe future versions of GPT and similar models will likely get this question right on the first try.