Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal

Abstract: LLMs excel at generating coherent text, and model compression techniques such as knowledge distillation have enabled their use in resource-constrained settings. However, these models can be biased in multiple ways, including the unfounded association of male and female genders with gender-neutral professions. Therefore, knowledge distillation without any fairness constraints may preserve or exaggerate the teacher model's biases onto the distilled model. To this end, we present a novel approach to mitigate gender disparity in text generation by learning a fair model during knowledge distillation. We propose two modifications to the base knowledge distillation based on counterfactual role reversal$\unicode{x2014}$modifying teacher probabilities and augmenting the training set. We evaluate gender polarity across professions in open-ended text generated from the resulting distilled and finetuned GPT$\unicode{x2012}$2 models and demonstrate a substantial reduction in gender disparity with only a minor compromise in utility. Finally, we observe that LLMs that reduce gender polarity in language generation do not improve embedding fairness or downstream classification fairness.