A specialized 8B-parameter language model trained on astronomy literature and synthetic Q&A matches GPT-4o on the AstroMLab-1 astronomy benchmark at a fraction of the cost.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
astro-ph.IM 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AstroMLab 3: Achieving GPT-4o Level Performance in Astronomy with a Specialized 8B-Parameter Large Language Model
A specialized 8B-parameter language model trained on astronomy literature and synthetic Q&A matches GPT-4o on the AstroMLab-1 astronomy benchmark at a fraction of the cost.