GRADIEND: Monosemantic Feature Learning within Neural Networks Applied to Gender Debiasing of Transformer Models

Code

• github.com/aieng-lab/gradiend
  Officialpytorch★ 1

Abstract

AI systems frequently exhibit and amplify social biases, including gender bias, leading to harmful consequences in critical areas. This study introduces a novel encoder-decoder approach that leverages model gradients to learn a single monosemantic feature neuron encoding gender information. We show that our method can be used to debias transformer-based language models, while maintaining other capabilities. We demonstrate the effectiveness of our approach across multiple encoder-only based models and highlight its potential for broader applications.

Tasks

Reproductions