Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models

This article, sourced from ArXiv, suggests a novel geometric approach to debiasing vision-language models. The title indicates a shift in perspective, viewing bias not as a single point but as a subspace, potentially leading to more effective debiasing strategies. The focus is on post-hoc debiasing, implying the research explores methods to mitigate bias after the model has been trained.