Fardin Ahsan Sakib

Trajectory-Guided Steering: Mitigating Spurious Feature Bias in Clinical Classification

Large language models rely on spurious features in clinical classification: swapping a single gender token in clinical notes alters gender-irrelevant diagnoses in up to 53.5% of cases. Existing inference-time corrections either need counterfactual data built around the specific spurious feature or behave unpredictably....