AstroLLaMA-Chat: Scaling AstroLLaMA with Conversational and Diverse Datasets
Ernest Perkowski, Rui Pan, Tuan Dung Nguyen, Yuan-Sen Ting, Sandor Kruk, Tong Zhang, Charlie O’Neill, M. Jabłońska, Zechang Sun, Michael J. Smith, Huiling Liu, Kevin Schawinski, Kartheik G. Iyer, Ioana Ciucă, UniverseTBD · Research Notes of the AAS · 2024
Abstract We explore the potential of enhancing LLM performance in astronomy-focused question-answering through targeted, continual pre-training. By employing a compact 7B-parameter LLaMA-2 model and focusing exclusively on a curated set of astronomy corpora—comprising abstracts, introductions, and conclusions—we achieve notable improvements in specialized topic comprehension. While general LLMs like GPT-4 excel in broader question-answering scenarios due to superior reasoning capabilities, our findings suggest that continual pre-training with limited resources can still enhance model performance on specialized topics. Additionally, we present an extension of AstroLLaMA: the fine-tuning of the 7B LLaMA model on a domain-specific conversational data set, culminating in the release of the chat-enabled AstroLLaMA for community use. Comprehensive quantitative benchmarking is currently in progress and will be detailed in an upcoming full paper. The model, AstroLLaMA-Chat, is now available at https://huggingface.co/universeTBD , providing the first open-source conversational AI tool tailored for the astronomy community.