RobustDebias: Debiasing Language Models using Distributionally Robust Optimization
This addresses bias issues in widely used language models, offering a scalable fine-tuning solution that is incremental over prior debiasing methods.
The paper tackles bias amplification during fine-tuning of pretrained language models like BERT, proposing RobustDebias using Distributionally Robust Optimization to significantly mitigate biases across demographics with minimal performance impact.
Pretrained language models have been shown to exhibit biases and social stereotypes. Prior work on debiasing these models has largely focused on modifying embedding spaces during pretraining, which is not scalable for large models. Fine-tuning pretrained models on task-specific datasets can both degrade model performance and amplify biases present in the fine-tuning data. We address bias amplification during fine-tuning rather than costly pretraining, focusing on BERT models due to their widespread use in language understanding tasks. While Empirical Risk Minimization effectively optimizes downstream performance, it often amplifies social biases during fine-tuning. To counter this, we propose \textit{RobustDebias}, a novel mechanism which adapts Distributionally Robust Optimization (DRO) to debias language models during fine-tuning. Our approach debiases models across multiple demographics during MLM fine-tuning and generalizes to any dataset or task. Extensive experiments on various language models show significant bias mitigation with minimal performance impact.