Massive Multitask Language Understanding
GPTKB entity
Statements (28)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:performance
|
gptkbp:abbreviation |
gptkb:MMLU
|
gptkbp:creator |
gptkb:Dawn_Song
gptkb:Jacob_Steinhardt Dan Hendrycks Mantas Mazeika Thomas Dietterich Yiming Liu |
gptkbp:domain |
gptkb:STEM
humanities social sciences other professional fields |
gptkbp:field |
gptkb:artificial_intelligence
natural language processing |
https://www.w3.org/2000/01/rdf-schema#label |
Massive Multitask Language Understanding
|
gptkbp:license |
gptkb:MIT_License
|
gptkbp:notableUser |
gptkb:Google
gptkb:OpenAI gptkb:Anthropic |
gptkbp:numberOfRooms |
over 15,000
|
gptkbp:numberOfTasks |
57
|
gptkbp:publicationYear |
2021
|
gptkbp:purpose |
evaluate language model performance
|
gptkbp:repository |
https://github.com/hendrycks/test
|
gptkbp:type |
multiple choice
|
gptkbp:usedFor |
benchmarking large language models
|
gptkbp:bfsParent |
gptkb:MMLU
|
gptkbp:bfsLayer |
7
|