From Prejudice to Parity: A New Approach to Debiasing Large Language Model Word Embeddings
Abstract: 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 \textit{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 \textit{DeepSoftDebias} outperforms the current state-of-the-art methods at reducing bias across gender, race and religion.
Paper Type: Long
Research Area: Interpretability and Analysis of Models for NLP
Research Area Keywords: Debiasing, Gender Bias, Racial Bias, Bias, LLM
Contribution Types: Model analysis & interpretability
Languages Studied: English
Submission Number: 519
Loading