From Prejudice to Parity: A New Approach to Debiasing Large Language Model Word Embeddings
This addresses bias in AI systems for users affected by discriminatory outputs, but it is incremental as it builds on prior debiasing work.
The paper tackled bias in large language model word embeddings by proposing DeepSoftDebias, a neural network-based algorithm for soft debiasing, and found that it outperforms state-of-the-art methods in reducing bias across gender, race, and religion.
Embeddings play a pivotal role in the efficacy of Large Language Models. They are the bedrock on which these models grasp contextual relationships and foster a more nuanced understanding of language and consequently perform remarkably on a plethora of complex tasks that require a fundamental understanding of human language. Given that these embeddings themselves often reflect or exhibit bias, it stands to reason that these models may also inadvertently learn this bias. In this work, we build on the seminal previous work and propose DeepSoftDebias, an algorithm that uses a neural network to perform 'soft debiasing'. We exhaustively evaluate this algorithm across a variety of SOTA datasets, accuracy metrics, and challenging NLP tasks. We find that DeepSoftDebias outperforms the current state-of-the-art methods at reducing bias across gender, race, and religion.