Papers with Code · CC BY-SA 4.0

General Knowledge

32 평가 기록 8 datasets

This task aims to evaluate the ability of a model to answer general-knowledge questions.

Source: BIG-bench

하위 태스크

NQ Natural Questions 2 데이터셋 · 20 rows MR Movie Recommendation 1 데이터셋 · 5 rows SA Similarities Abstraction 1 데이터셋 · 2 rows GF Global Facts 1 데이터셋 · 1 rows M Miscellaneous 1 데이터셋 · 1 rows T TriviaQA 1 데이터셋 · 1 rows SU Sports Understanding 0 데이터셋 · 0 rows