On Bias and Fairness in NLP: Investigating the Impact of Bias and Debiasing in Language Models on the Fairness of Toxicity Detection

Language models are the new state-of-the-art NLP models and they are being increasingly used in many NLP tasks. Even though there is evidence that language models are biased, the impact of that bias on the fairness of downstream NLP tasks is still understudied. Furthermore, despite that numerous debiasing methods have been proposed in the literature, the impact of bias removal methods on the fairness of NLP tasks is also understudied. In this work, we investigate three different sources of bias in NLP models, i.e. representation bias, selection bias and overamplification bias, and examine how they impact the fairness of the downstream task of toxicity detection. Moreover, we investigate the impact of removing these biases using different bias removal techniques on the fairness of toxicity detection. Results show strong evidence that downstream sources of bias, especially overamplification bias, are the most impactful types of bias on the fairness of the task of toxicity detection. We also found strong evidence that removing overamplification bias by fine-tuning the language models on a dataset with balanced contextual representations and ratios of positive examples between different identity groups can improve the fairness of the task of toxicity detection. Finally, we build on our findings and introduce a list of guidelines to ensure the fairness of the task of toxicity detection.