知识卡片
显著性图与注意力图含义不同
注意力图展示某些内部权重,显著性方法则按自身定义估计输入变化或梯度与输出的关系。它们提供不同诊断线索,不能统称为模型“最关注”的真实原因;解释结论需注明方法与目标输出。
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
- · 按任务适配模型
原书出处 · 1 处
- · 查看原书依据
Salience maps, which show parts of the input that are paid most attention to by the model Visualization of embeddings Counterfactual analysis that shows how your model behavior changes after a change to the input like adding or removing a token. Exercise Using the sentences in the Canadian parliamentary proceedings dataset in the book’s GitHub repository, classify the sentences based on the tone of their
参考来源
- 位置:《Designing Large Language Model Applications》第05章《按任务适配模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Designing Large Language Model Applications/_epub-src/OEBPS/ch05.html)
- 结论依据:摘录中关于显著性图与注意力图含义不同的定义、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:Salience maps, which show parts of the input that are paid most attention to by the model Visualization of embeddings Counterfactual analysis that shows how your model behavior changes after a change to the input like adding or removing a token. Exercise Using the sentences in the Canadian parliamentary proceedings dataset in the book’s GitHub repository, classify the sentences based on the tone of their