原书出处
Designing Large Language Model Applications
Recall/completeness What content merits inclusion in the summary is a difficult question, especially if there is a hard limit on the summary length. You can train a ranking model that ranks sentences in the source document by importance, and then verify if the top-ranked sentences are represented in the summary. You can also specify beforehand the type of content that you need represented in the
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/ch10.html
EPUB SHA-256:1b4d2347fec2f949fcddfbaf4fad597a1ae20887a096cfae64c59a619b4781bf