Mahalanobis-Smoothed Trust Conformal Prediction under Limited Calibration Data

Conformal prediction endows any classifier with a distribution-free coverage guarantee, yet under limited calibration data the guarantee is nearly vacuous: the returned prediction sets routinely grow to almost the size of the full label space, eroding the very utility they are meant to provide. We trace this failure to a structural blind spot shared by every published conformity score: each reads the model solely through the post-softmax probability vector—a bottleneck that discards the class-conditional geometry the encoder has already computed, and which often separates the classes more cleanly than the linear head that projects them. We show that this geometry can be handed back to the calibration pipeline at negligible cost: because every encoder already computes a hidden state alongside its logits, a simple per-class distance to training-set centroids recovers exactly the structure the softmax throws away. \methodlong (\method) builds on this observation—it blends the centroid distance with the familiar rank-regularised score on temperature-scaled logits, and a holdout slice of the calibration data picks the blend for each deployment—so the score leans on geometry where it helps and safely falls back to the softmax ranking where it does not. The guarantee survives this adaptivity on one condition, a data-handling discipline: the geometric statistics must be estimated on training data—estimating them on the calibration set breaks exchangeability and inflates set size by $30.9\%$. Across $18$ cells of an LLM-style sequence-classification benchmark, \method delivers the smallest prediction set in $5/6$ settings and the smallest average against nine published baselines, reducing average set size by $44.3\%$ over APS, $12.3\%$ over RAPS, and $4.9\%$ over the strongest competing baseline, while preserving the requested marginal coverage to within $\pm 0.02$ in every evaluated cell.