AstroLLaMA: Towards Specialized Foundation Models in Astronomy

09/12/2023

∙

Large language models excel in many human-language tasks but often falter in highly specialized domains like scholarly astronomy. To bridge this gap, we introduce AstroLLaMA, a 7-billion-parameter model fine-tuned from LLaMA-2 using over 300,000 astronomy abstracts from arXiv. Optimized for traditional causal language modeling, AstroLLaMA achieves a 30 showing marked domain adaptation. Our model generates more insightful and scientifically relevant text completions and embedding extraction than state-of-the-arts foundation models despite having significantly fewer parameters. AstroLLaMA serves as a robust, domain-specific model with broad fine-tuning potential. Its public release aims to spur astronomy-focused research, including automatic paper summarization and conversational agent development.

READ FULL TEXT

AstroLLaMA: Towards Specialized Foundation Models in Astronomy

Llama 2: Open Foundation and Fine-Tuned Chat Models

Efficient domain adaptation of language models in ASR systems using Prompt-tuning

Unsupervised Domain Adaptation with Adapter

Recycling diverse models for out-of-distribution generalization

Localising In-Domain Adaptation of Transformer-Based Biomedical Language Models

A Critical Review of Large Language Models: Sensitivity, Bias, and the Path Toward Specialized AI

Platypus: Quick, Cheap, and Powerful Refinement of LLMs

AstroLLaMA: Towards Specialized Foundation Models in Astronomy

Related Research

Llama 2: Open Foundation and Fine-Tuned Chat Models

Efficient domain adaptation of language models in ASR systems using Prompt-tuning

Unsupervised Domain Adaptation with Adapter

Recycling diverse models for out-of-distribution generalization

Localising In-Domain Adaptation of Transformer-Based Biomedical Language Models

A Critical Review of Large Language Models: Sensitivity, Bias, and the Path Toward Specialized AI

Platypus: Quick, Cheap, and Powerful Refinement of LLMs