arXiv:2610.22618v1 Announce Type: new Abstract: 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. We observe that how a model's preference between answers evolves across layers, its prediction trajectory, indicates for each document whether a correction is likely to help. We propose Trajectory-Guided Steering (TGS), which decides from the trajectory alone whether to correct each prediction and in which direction, with no counterfactual data and no knowledge of the spurious feature. On 16 clinical classification tasks from i2b2, TGS fixes 17.7% of errors while breaking only 1.3% of correct predictions and stays net-positive across all tested hyperparameter settings; all baselines are net-negative or near zero. The same corrections reduce reliance on the spurious feature: on the most affected diseases, gender-swap inconsistency falls sharply (hypertension 53.5% -> 38.0%, diabetes 35.1% -> 21.5%). Applying the correction to every document instead raises breaks on correct positive predictions from 0.1% to 6.4%, so per-document selection is essential. TGS also transfers to three model families and three other clinical and biomedical datasets.
Functional Welfare for AI Safety