A Robust Evaluation of Probe Robustness: Lessons for Reliable OOD Uncertainty Quantification
ProbeDrift is introduced, a systematic evaluation framework for supervised uncertainty probes covering a wide range of OOD settings across models, tasks, and distributional shifts, and it is argued that robust uncertainty estimation requires robust evaluation.
Joe Stacey, Hadas Orgad, Kentaro Inui et al.
· 0 citations