Evaluating the Effectiveness of Large Language Models in Representing Textual Descriptions of Geometry and Spatial Relations
This work addresses the problem of improving geospatial AI applications by evaluating foundation models, but it is incremental as it highlights existing limitations without proposing new solutions.
The study assessed how well large language models like GPT-2 and BERT represent geometric and spatial information from text, finding they achieved up to 73% accuracy in capturing some relations but struggled with numeric values and object retrieval.
This research focuses on assessing the ability of large language models (LLMs) in representing geometries and their spatial relations. We utilize LLMs including GPT-2 and BERT to encode the well-known text (WKT) format of geometries and then feed their embeddings into classifiers and regressors to evaluate the effectiveness of the LLMs-generated embeddings for geometric attributes. The experiments demonstrate that while the LLMs-generated embeddings can preserve geometry types and capture some spatial relations (up to 73% accuracy), challenges remain in estimating numeric values and retrieving spatially related objects. This research highlights the need for improvement in terms of capturing the nuances and complexities of the underlying geospatial data and integrating domain knowledge to support various GeoAI applications using foundation models.