StereoSet: Measuring stereotypical bias in pretrained language models
Active
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.
- Domain
- Safeguards
- License
- mit
- Published
- Jun 2025
- Notable for
- Benchmark for evaluating Safeguards.
Cite
Notes
Only stored in your browser.
FAQ
- What is 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.
- What license is StereoSet: Measuring stereotypical bias in pretrained language models under?
- StereoSet: Measuring stereotypical bias in pretrained language models is available under mit.