原书出处
Designing Large Language Model Applications
If you are using encoder-only models like BERT, the output probability scores can be used as the measure of confidence. Thus, a group of well-calibrated models will enable us to efficiently route the input to the most suitable model. (Recall our discussion on model calibration in Chapter 5.)
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/ch13.html
EPUB SHA-256:1b4d2347fec2f949fcddfbaf4fad597a1ae20887a096cfae64c59a619b4781bf