Efficient and Interpretable Transformer for Counterfactual Fairness

ArXi:2604.26188v1 Announce Type: new The growing reliance of machine learning models in high-stakes, highly regulated domains such as finance and insurance has created a growing tension between predictive performance, interpretability, and regulatory fairness requirements. In these settings, models are expected not only to deliver reliable predictions but also to provide transparent decision rationales and comply with strict fairness requirements.