evaluation-task · Source-linked discovery
StereoSet: Measuring stereotypical bias in pretrained language models
A dataset that measures stereotype bias in language models across gender, race, religion, and profession domains. Models choose between stereotype, anti-stereotype, and unrelated completions to sentences.
OriginMoin Nadeem, Anna Bethke, Siva ReddyTopicsGeneral capabilityStatusimported
Can support
Not independently assessed by FronteraEval yet.
Cannot support by itself
No inference beyond the upstream source should be made until the protocol is reviewed.