FathomGPT: A Natural Language Interface for Interactively Exploring Ocean Science Data
This work addresses the challenge for marine scientists of efficiently accessing and analyzing complex ocean data through a user-friendly interface, though it is incremental as it applies existing language models to a specific domain.
The researchers tackled the problem of exploring ocean science data by developing FathomGPT, a natural language interface that enables interactive querying and analysis of the FathomNet image database, resulting in a system that facilitates free-form exploration and optimizes response times.
We introduce FathomGPT, an open source system for the interactive investigation of ocean science data via a natural language interface. FathomGPT was developed in close collaboration with marine scientists to enable researchers to explore and analyze the FathomNet image database. FathomGPT provides a custom information retrieval pipeline that leverages OpenAI's large language models to enable: the creation of complex queries to retrieve images, taxonomic information, and scientific measurements; mapping common names and morphological features to scientific names; generating interactive charts on demand; and searching by image or specified patterns within an image. In designing FathomGPT, particular emphasis was placed on enhancing the user's experience by facilitating free-form exploration and optimizing response times. We present an architectural overview and implementation details of FathomGPT, along with a series of ablation studies that demonstrate the effectiveness of our approach to name resolution, fine tuning, and prompt modification. We also present usage scenarios of interactive data exploration sessions and document feedback from ocean scientists and machine learning experts.