A two-stage LLM framework infers stellar parameters and ~20 elemental abundances from spectra, with performance improving systematically as training data volume increases.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
astro-ph.IM 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Spectra as Language: Large Language Models for Scalable Stellar Parameter and Abundance Inference
A two-stage LLM framework infers stellar parameters and ~20 elemental abundances from spectra, with performance improving systematically as training data volume increases.