Perkowski, Ernest
AstroLLaMA-Chat: Scaling AstroLLaMA with Conversational and Diverse Datasets
Perkowski, Ernest, Pan, Rui, Nguyen, Tuan Dung, Ting, Yuan-Sen, Kruk, Sandor, Zhang, Tong, O'Neill, Charlie, Jablonska, Maja, Sun, Zechang, Smith, Michael J., Liu, Huiling, Schawinski, Kevin, Iyer, Kartheik, UniverseTBD, Ioana Ciucă for
To enhance this, we introduce AstroLLaMA-Chat, an advanced version of AstroLLaMA. This new iteration broadens the training scope to include introductions and conclusions of papers, alongside abstracts, as these sections are often rich in pivotal information for question-answering tasks. We initiated by downloading all papers up to July 2023, including all the files that come with a submission to arXiv. The data has been further refined for optimal operability, retaining only files with ".tex" suffixes. Through a multi-stage process, and utilising a comprehensive regex matching process, the extraction of the targeted sections was performed. Given the diverse LaTeX formatting standards, approximately 90% of the samples remained post-processing. Subsequently, we removed specific formatting patterns, comments, and superfluous symbols like newlines to ensure the readability of the training data. Further, we have fine-tuned AstroLLaMA-Chat on a domain-specific dialogue dataset. To generate Question-Answer pairs, we engaged GPT-4 (OpenAI 2023) to formulate pertinent questions from paragraphs within 300,000 arXiv papers, with GPT-4 also tasked with answering these questions by retrieving context-relevant information.
AstroLLaMA: Towards Specialized Foundation Models in Astronomy
Nguyen, Tuan Dung, Ting, Yuan-Sen, Ciucă, Ioana, O'Neill, Charlie, Sun, Ze-Chang, Jabłońska, Maja, Kruk, Sandor, Perkowski, Ernest, Miller, Jack, Li, Jason, Peek, Josh, Iyer, Kartheik, Różański, Tomasz, Khetarpal, Pranav, Zaman, Sharaf, Brodrick, David, Méndez, Sergio J. Rodríguez, Bui, Thang, Goodman, Alyssa, Accomazzi, Alberto, Naiman, Jill, Cranney, Jesse, Schawinski, Kevin, UniverseTBD, null
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% lower perplexity than Llama-2, 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.