cosmosage: A Natural-Language Assistant for Cosmologists
Tijmen de Haan

TL;DR
cosmosage is a large language model-based natural-language assistant designed specifically for cosmology, enabling users ranging from laypersons to experts to access and reason about cosmological knowledge effectively.
Contribution
This paper introduces cosmosage, a specialized LLM for cosmology that outperforms general-purpose models on cosmology question-answering tasks.
Findings
cosmosage achieves state-of-the-art performance in cosmology question-answering
The model is trained on a large corpus of textbooks and papers
Code and parameters are publicly available
Abstract
cosmosage is a natural-language assistant intended for a wide audience, from laypersons interested in cosmology to students, teachers, and professional cosmologists. cosmosage provides a novel way to access knowledge and reason about cosmology. Leveraging the power of advanced large language models (LLMs), cosmosage has learned from a vast corpus of open-access source texts, including textbooks and papers. cosmosage is found to be state-of-the-art on the narrow task of answering questions about cosmology, outperforming all general-purpose models. The model parameters and code are publicly available.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsComputational Physics and Python Applications · Science and Climate Studies
