StereoSet
Language Model EvaluationEnglish
StereoSet is a language model evaluation-focused dataset in English that provides 17 labeled examples distributed in JSON format.
About StereoSet
Dataset that measures stereotype bias in language models. StereoSet consists of 17,000 sentences that measures model preferences across gender, race, religion, and profession.
Details
- Task
- Language Model Evaluation
- Language
- English
- Format
- JSON
- Rows / instances
- 17
- Creator
- Nadeem et al.
- Year
- 2020