Towards Region-aware Bias Evaluation Metrics

AbstractWhen exposed to human-generated data, language models are known to learn and amplify societal biases. While previous works introduced metrics that can be used to assess the bias in these models, they rely on assumptions that may not be universally true. For instance, a gender bias dimension commonly used by these metrics is that of family–career, but this may not be the only common bias in certain regions of the world. In this paper, we identify topical differences in gender bias across different regions and propose a region-aware bottom-up approach for bias assessment. Several of our proposed region-aware gender bias dimensions are found to be aligned with the human perception of gender biases in these regions.