Galactic ChitChat: Using Large Language Models to Converse with Astronomy Literature
This work addresses the challenge of efficiently processing and engaging with astronomy papers for researchers, though it is incremental as it applies existing methods to a new domain.
The paper tackled the problem of using large language models to interact with astronomy literature by employing a distillation technique that reduces input size by 50% while maintaining structure, and found that GPT-4 excels in multi-document contexts, providing detailed answers.
We demonstrate the potential of the state-of-the-art OpenAI GPT-4 large language model to engage in meaningful interactions with Astronomy papers using in-context prompting. To optimize for efficiency, we employ a distillation technique that effectively reduces the size of the original input paper by 50\%, while maintaining the paragraph structure and overall semantic integrity. We then explore the model's responses using a multi-document context (ten distilled documents). Our findings indicate that GPT-4 excels in the multi-document domain, providing detailed answers contextualized within the framework of related research findings. Our results showcase the potential of large language models for the astronomical community, offering a promising avenue for further exploration, particularly the possibility of utilizing the models for hypothesis generation.