StereoSet

Dataset Information
Languages
English
License
Homepage

Overview

A large-scale natural dataset in English to measure stereotypical biases in four domains: gender, profession, race, and religion.

Source: StereoSet: Measuring stereotypical bias in pretrained language models

Variants: StereoSet

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Bias Detection GAL 120B Galactica: A Large Language Model … 2022-11-16
Bias Detection GPT-3 (text-davinci-002) Galactica: A Large Language Model … 2022-11-16
Bias Detection OPT 175B Galactica: A Large Language Model … 2022-11-16
Bias Detection BERT (base) StereoSet: Measuring stereotypical bias in … 2020-04-20
Bias Detection GPT-2 (large) StereoSet: Measuring stereotypical bias in … 2020-04-20
Bias Detection GPT-2 (small) StereoSet: Measuring stereotypical bias in … 2020-04-20
Bias Detection RoBERTa (base) StereoSet: Measuring stereotypical bias in … 2020-04-20
Bias Detection XLNet (base) StereoSet: Measuring stereotypical bias in … 2020-04-20
Bias Detection BERT (large) StereoSet: Measuring stereotypical bias in … 2020-04-20
Bias Detection XLNet (large) StereoSet: Measuring stereotypical bias in … 2020-04-20
Bias Detection GPT-2 (medium) StereoSet: Measuring stereotypical bias in … 2020-04-20

Research Papers

Recent papers with results on this dataset: