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.

Open interactive record →
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.

Original sources