microsoft / promptbase

All things prompt engineering
MIT License
5.44k stars 302 forks source link

mentioned datasets #54

Open CaipingPeng opened 1 month ago

CaipingPeng commented 1 month ago

hi, I noticed your paper mentioned MedQA、PubMedQA、MedMCQA datasets, But I can‘t find any method to evaluate model performance on these datasets.

How to solve this prob? It will be helpful ,thank you.