# A systematic review of geospatial location embedding approaches in large language models: A path to spatial AI systems

arXiv: https://arxiv.org/abs/2401.10279 · HTML: https://mlsanity.com/paper/2401.10279/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 34 references that are in the map.
- First posted on arXiv 12 Jan 2024.

## Builds on (most cited first, 11 of 11)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook](https://mlsanity.com/paper/2310.10196/) (2023)
- [GeoLLM: Extracting Geospatial Knowledge from Large Language Models](https://mlsanity.com/paper/2310.06213/) (2023)
- [A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challenge](https://mlsanity.com/paper/2310.11703/) (2023)
- [Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messages](https://mlsanity.com/paper/2310.09340/) (2023)
- [Evaluating the Effectiveness of Large Language Models in Representing Textual Descriptions of Geometry and Spatial Relations](https://mlsanity.com/paper/2307.03678/) (2023)
- [FREE: The Foundational Semantic Recognition for Modeling Environmental Ecosystems](https://mlsanity.com/paper/2311.10255/) (2023)
- [Chatmap : Large Language Model Interaction with Cartographic Data](https://mlsanity.com/paper/2310.01429/) (2023)
- [Automatic extraction of road intersection points from USGS historical map series using deep convolutional neural networks](https://mlsanity.com/paper/2007.07404/) (2020)
- [Core Building Blocks: Next Gen Geo Spatial GPT Application](https://mlsanity.com/paper/2310.11029/) (2023)
- [Is ChatGPT a game changer for geocoding -- a benchmark for geocoding address parsing techniques](https://mlsanity.com/paper/2310.14360/) (2023)

## Built on by (most cited first, 6 of 6)

- [Foundation Models for Geospatial Reasoning: Assessing Capabilities of Large Language Models in Understanding Geometries and Topological Spatial Relations](https://mlsanity.com/paper/2505.17136/) (2025)
- [Graph Canvas for Controllable 3D Scene Generation](https://mlsanity.com/paper/2412.00091/) (2024)
- [From reactive to cognitive: brain-inspired spatial intelligence for embodied agents](https://mlsanity.com/paper/2508.17198/) (2025)
- [Pan-Arctic Permafrost Landform and Human-built Infrastructure Feature Detection with Vision Transformers and Location Embeddings](https://mlsanity.com/paper/2506.02868/) (2025)
- [Enabling Intrinsic Reasoning over Dense Geospatial Embeddings with DFR-Gemma](https://mlsanity.com/paper/2604.07490/) (2026)
- [Toward Governance-Aware Autonomous GIS: A Narrative Review of Ethical and Privacy Risks in LLM-Enabled GeoAI](https://mlsanity.com/paper/2609.16232/) (2026)

## Abstract (arXiv)

Geospatial Location Embedding (GLE) helps a Large Language Model (LLM) assimilate and analyze spatial data. GLE emergence in Geospatial Artificial Intelligence (GeoAI) is precipitated by the need for deeper geospatial awareness in our complex contemporary spaces and the success of LLMs in extracting deep meaning in Generative AI. We searched Google Scholar, Science Direct, and arXiv for papers on geospatial location embedding and LLM and reviewed articles focused on gaining deeper spatial "knowing" through LLMs. We screened 304 titles, 30 abstracts, and 18 full-text papers that reveal four GLE themes - Entity Location Embedding (ELE), Document Location Embedding (DLE), Sequence Location Embedding (SLE), and Token Location Embedding (TLE). Synthesis is tabular and narrative, including a dialogic conversation between "Space" and "LLM." Though GLEs aid spatial understanding by superimposing spatial data, they emphasize the need to advance in the intricacies of spatial modalities and generalized reasoning. GLEs signal the need for a Spatial Foundation/Language Model (SLM) that embeds spatial knowing within the model architecture. The SLM framework advances Spatial Artificial Intelligence Systems (SPAIS), establishing a Spatial Vector Space (SVS) that maps to physical space. The resulting spatially imbued Language Model is unique. It simultaneously represents actual space and an AI-capable space, paving the way for AI native geo storage, analysis, and multi-modality as the basis for Spatial Artificial Intelligence Systems (SPAIS).