A single end-to-end Transformer model unifies stellar labels from heterogeneous spectroscopic surveys into a self-consistent scale without post-hoc recalibration.
org/abs/1807.03888
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Multi-layer SAE transitions capture domain-specific signatures that distinguish OOD texts in Gemma-2 models.
Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.
citing papers explorer
-
Homogeneous Stellar Parameters from Heterogeneous Spectra with Deep Learning
A single end-to-end Transformer model unifies stellar labels from heterogeneous spectroscopic surveys into a self-consistent scale without post-hoc recalibration.
-
Domain Restriction via Multi SAE Layer Transitions
Multi-layer SAE transitions capture domain-specific signatures that distinguish OOD texts in Gemma-2 models.
-
Language Models (Mostly) Know What They Know
Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.