English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We explore the potential of enhancing LLM performance in astronomy-focusedquestion-answering through targeted, continual pre-training. By employing acompact 7B-parameter LLaMA-2 model and focusing exclusively on a curated set ofastronomy corpora -- comprising abstracts, introductions, and conclusions -- weachieve notable improvements in specialized topic comprehension. While generalLLMs like GPT-4 excel in broader question-answering scenarios due to superiorreasoning capabilities, our findings suggest that continual pre-training withlimited resources can still enhance model performance on specialized topics.Additionally, we present an extension of AstroLLaMA: the fine-tuning of the 7BLLaMA model on a domain-specific conversational dataset, culminating in therelease of the chat-enabled AstroLLaMA for community use. Comprehensivequantitative benchmarking is currently in progress and will be detailed in anupcoming full paper. The model, AstroLLaMA-Chat, is now available athttps://huggingface.co/universeTBD, providing the first open-sourceconversational AI tool tailored for the astronomy community.

AstroLLaMA-Chat: Scaling AstroLLaMA with Conversational and Diverse Datasets