English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This research focuses on assessing the ability of large language models(LLMs) in representing geometries and their spatial relations. We utilize LLMsincluding GPT-2 and BERT to encode the well-known text (WKT) format ofgeometries and then feed their embeddings into classifiers and regressors toevaluate the effectiveness of the LLMs-generated embeddings for geometricattributes. The experiments demonstrate that while the LLMs-generatedembeddings can preserve geometry types and capture some spatial relations (upto 73% accuracy), challenges remain in estimating numeric values and retrievingspatially related objects. This research highlights the need for improvement interms of capturing the nuances and complexities of the underlying geospatialdata and integrating domain knowledge to support various GeoAI applicationsusing foundation models.

Evaluating the Effectiveness of Large Language Models in Representing Textual Descriptions of Geometry and Spatial Relations