The Elephant in the Room: Exploring the Role of Neutral Words in Language Model Group-Agnostic Debiasing

Large language models (LLMs) are increasingly integrated into our daily lives, raising significant ethical concerns, especially about perpetuating stereotypes. While group-specific debiasing methods have made progress, they often fail to address multiple biases simultaneously. In contrast, group-agnostic debiasing has the potential to mitigate a variety of biases at once, but remains underexplored. In this work, we investigate the role of neutral words-the group-agnostic component-in enhancing the group-agnostic debiasing process. We first reveal that neutral words are essential for preserving semantic modeling, and we propose ϵ-DPCE, a method that incorporates a neutral word semantics-based loss function to effectively alleviate the deterioration of the Language Modeling Score (LMS) during the debiasing process. Furthermore, by introducing the SCM-Projection method, we demonstrate that SCM-based debiasing eliminates stereotypes by indirectly disrupting the association between attribute and neutral words in the Stereotype Content Model (SCM) space. Our experiments show that neutral words, which often embed multi-group stereotypical objects, play a key role in contributing to the group-agnostic nature of SCM-based debiasing.