FineDeb: A Debiasing Framework for Language Models

Abstract: As LLMs are increasingly included in human-facing machine learning tools, bias against demographic subgroups has gained attention. We propose FineDeb, a two-phase debiasing framework for LLMs that starts with contextual debiasing of embeddings learned by pretrained LLMs. The model is then fine-tuned on a language modeling objective. Our results show that FineDeb offers stronger debiasing in comparison to other methods which often result in models as biased as the original LLM. Our framework is generalizable for demographics with multiple classes, and we demonstrate its effectiveness through extensive experiments and comparisons with state of the art techniques. We release our code and data on GitHub.