JSALT2024 Evaluating LLMs for Research Astronomy

community

https://www.clsp.jhu.edu/evaluating-llm-performance-in-research-astronomy/

jsalt2024-evaluating-llms-for-astronomy

AI & ML interests

Scientific research, large language models, retrieval, evaluations

kiyer

authored 2 papers 7 months ago

The Multimodal Universe: Enabling Large-Scale Machine Learning with 100TB of Astronomical Scientific Data

Paper • 2412.02527 • Published Dec 3, 2024 • 12

Red, hot, and very metal poor: extreme properties of a massive accreting black hole in the first 500 Myr

Paper • 2412.04983 • Published Dec 6, 2024

kiyer

authored 3 papers 11 months ago

AstroLLaMA-Chat: Scaling AstroLLaMA with Conversational and Diverse Datasets

Paper • 2401.01916 • Published Jan 3, 2024 • 1

pathfinder: A Semantic Framework for Literature Review and Knowledge Discovery in Astronomy

Paper • 2408.01556 • Published Aug 2, 2024 • 3

Disentangling Dense Embeddings with Sparse Autoencoders

Paper • 2408.00657 • Published Aug 1, 2024 • 1

charlieoneill

updated 2 models about 1 year ago

JSALT2024-Astro-LLMs/astro-embeddings

Updated Jul 29, 2024

JSALT2024-Astro-LLMs/cs-embeddings

Updated Jul 23, 2024

kiyer

updated a dataset about 1 year ago

JSALT2024-Astro-LLMs/astro_paper_corpus

Viewer • Updated Jul 11, 2024 • 272k • 23 • 2

kiyer

authored a paper almost 2 years ago

AstroLLaMA: Towards Specialized Foundation Models in Astronomy

Paper • 2309.06126 • Published Sep 12, 2023 • 18