Data Bias According to Bipol: Men are Naturally Right and It is the Role of Women to Follow Their Lead
This work addresses the problem of social bias in datasets for AI researchers and practitioners, but it is incremental as it extends existing bias detection methods to new languages and datasets.
The study introduced new large labeled datasets in three languages to estimate social bias, confirming that many datasets, including benchmark ones, exhibit male bias and other types of prejudice, with findings based on experiments across 10 datasets totaling nearly 6 million samples.
We introduce new large labeled datasets on bias in 3 languages and show in experiments that bias exists in all 10 datasets of 5 languages evaluated, including benchmark datasets on the English GLUE/SuperGLUE leaderboards. The 3 new languages give a total of almost 6 million labeled samples and we benchmark on these datasets using SotA multilingual pretrained models: mT5 and mBERT. The challenge of social bias, based on prejudice, is ubiquitous, as recent events with AI and large language models (LLMs) have shown. Motivated by this challenge, we set out to estimate bias in multiple datasets. We compare some recent bias metrics and use bipol, which has explainability in the metric. We also confirm the unverified assumption that bias exists in toxic comments by randomly sampling 200 samples from a toxic dataset population using the confidence level of 95% and error margin of 7%. Thirty gold samples were randomly distributed in the 200 samples to secure the quality of the annotation. Our findings confirm that many of the datasets have male bias (prejudice against women), besides other types of bias. We publicly release our new datasets, lexica, models, and codes.