Bias Benchmarks

AbstractRecent work has shown pre-trained language models capture social biases from the large amounts of text they are trained on. This has attracted attention to developing techniques that mitigate such …...

AbstractExisting bias mitigation methods require social-group-specific word pairs (e.g., “man” – “woman”) for each social attribute (e.g., gender), restricting the bias mitigation to only one specified social attribute. Further, this …...