Galactic ChitChat: Using Large Language Models to Converse with Astronomy Literature
Abstract
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- April 2023
- DOI:
- 10.48550/arXiv.2304.05406
- arXiv:
- arXiv:2304.05406
- Bibcode:
- 2023arXiv230405406C
- Keywords:
-
- Computer Science - Computation and Language;
- Astrophysics - Astrophysics of Galaxies;
- Astrophysics - Instrumentation and Methods for Astrophysics
- E-Print:
- 3 pages, submitted to RNAAS, comments very welcome from the community