HuskyInSalt / CRAG

Corrective Retrieval Augmented Generation
304 stars 29 forks source link

About the test set of evaluators #14

Open pengyxhack opened 7 months ago

pengyxhack commented 7 months ago

Hello, this is a very interesting work! May I ask if it's possible to provide the test set for evaluating the accuracy of the evaluator? Thank you very much.

HuskyInSalt commented 5 months ago

Hi, @pengyxhack ! We directly evaluated our evaluator on the PopQA test set in our paper. You can refer to Self-RAG for more details.