← 返回卡片

原书出处

Designing Large Language Model Applications

First Edition · 核验版本的摘录快照 · 导入于 2026-11-14T13:54:13.951Z

LLMs Struggle with the Long-Tail LLMs typically need a lot of samples to memorize a fact. The memorization ability is probabilistic, so we cannot predict the exact number of samples the LLM needs to see during training for it to memorize. This sample-inefficiency means that the LLM will struggle to answer questions about entities and concepts that rarely occur in the training data. As an

此预览只包含定位所需的摘录和上下文。

原书定位详情

来源:a19c7933-4eda-4176-aebd-30fe7e1ad292

正文位置:extracted/Designing Large Language Model Applications/_epub-src/OEBPS/ch12.html

EPUB SHA-256:1b4d2347fec2f949fcddfbaf4fad597a1ae20887a096cfae64c59a619b4781bf