arXiv:2512.08121v1 Announce Type: cross
Abstract: Rigorous evaluation of large language models (LLMs) relies on comparing models by the prevalence of desirable or undesirable behaviors, such as task pass rates or policy violations. These prevalence estimates are produced by a classifier, either an LLM-as-a-judge or human annotators, making the choice of classifier central to trustworthy evaluation. Common metrics used for this choice, such as Accuracy, Precision, and F1, are sensitive to class imbalance and to arbitrary choices of positive class, and can favor judges that distort prevalence estimates. We show that Youden’s $J$ statistic is theoretically aligned with choosing the best judge to compare models, and that Balanced Accuracy is an equivalent linear transformation of $J$. Through both analytical arguments and empirical examples and simulations, we demonstrate how selecting judges using Balanced Accuracy leads to better, more robust classifier selection.
Magnification-Aware Distillation (MAD): A Self-Supervised Framework for Unified Representation Learning in Gigapixel Whole-Slide Images
arXiv:2512.14796v1 Announce Type: cross Abstract: Whole-slide images (WSIs) contain tissue information distributed across multiple magnification levels, yet most self-supervised methods treat these scales as independent