MMLU benchmark introduced in paper: Measuring Massive Multitask Language Understanding (Hendrycks et al., 2020).
Predicate
introduced_in_paper
Object
Measuring Massive Multitask Language Understanding (Hendrycks et al., 2020)
Primary source · preprint · 2020-09-07
Measuring Massive Multitask Language Understanding — arXiv (Hendrycks et al.)