Supervised Bias Detection in Transformers-based Language Models

Training Large Language Models on biased datasets tends to teach a discriminatory behavior to the systems themselves, as it has been proven by the last years literature on fairness in AI and Machine Learning algorithms. The developed bias-detection strategies often ignores the inner body of the model, making it easy to generalize the methodology, but harder to understand the underlying motivations. In this paper, we present a general approach for detecting unwanted prejudices in Language Models, requiring only a small set of input data. Our strategy works on the embedding representation of languages, without any constraint on model architecture, but it is able to detect which parts of the representation is the most prejudice-affected. © 2024 Copyright for this paper by its authors.