Temperature scaling of density-matrix eigenvalues from LLM semantic embeddings optimizes proper-score calibration and corrects systematic overconfidence so entropy equals risk.
Conference on Learning Theory , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
Exploiting data symmetries boosts k-NN to select near-optimal low-noise subsets from noisy datasets, approaching Bayes-optimal performance in high dimensions, with learned representations aiding partial symmetry knowledge.
citing papers explorer
-
Eigenvalue Calibration for Semantic Embeddings of Large Language Models
Temperature scaling of density-matrix eigenvalues from LLM semantic embeddings optimizes proper-score calibration and corrects systematic overconfidence so entropy equals risk.
-
Leveraging Data Symmetries to Select an Optimal Subset of Training Data under Label Noise
Exploiting data symmetries boosts k-NN to select near-optimal low-noise subsets from noisy datasets, approaching Bayes-optimal performance in high dimensions, with learned representations aiding partial symmetry knowledge.