Coordinates from Context: Using LLMs to Ground Complex Location References

• URL: http://arxiv.org/abs/2510.08741v1
• Date: Thu, 09 Oct 2025 18:51:52 GMT
• Title: Coordinates from Context: Using LLMs to Ground Complex Location References
• Abstract summary: Geocoding is the task of linking a location reference to an actual geographic location.<n>We show that a relatively small fine-tuned LLM can achieve comparable performance with much larger off-the-shelf models.
• Score: 1.016973253129328
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Geocoding is the task of linking a location reference to an actual geographic location and is essential for many downstream analyses of unstructured text. In this paper, we explore the challenging setting of geocoding compositional location references. Building on recent work demonstrating LLMs' abilities to reason over geospatial data, we evaluate LLMs' geospatial knowledge versus reasoning skills relevant to our task. Based on these insights, we propose an LLM-based strategy for geocoding compositional location references. We show that our approach improves performance for the task and that a relatively small fine-tuned LLM can achieve comparable performance with much larger off-the-shelf models.

Related papers

• GeoBenchLLM: A Comprehensive Benchmark for Evaluating LLMs on Geo-Related Tasks [1.5249435285717097]
  We present benchName, a benchmark for probing Large Language Models on geo-related tasks.<n>We leverage a careful selection of twelve publicly available datasets from diverse geo-related tasks and domains.<n>Our results show that reasoning and size have a strong impact on overall performance.
  arXiv  Detail & Related papers  (2026-08-07T16:58:04Z)
• Enabling Intrinsic Reasoning over Dense Geospatial Embeddings with DFR-Gemma [23.95968681381851]
  Direct Feature Reasoning-Gemma (DFRGemma) is a novel framework that enables Large Language Models (LLMs) to reason directly over dense geospatial embeddings.<n>We introduce a multi-task benchmark that pairs embeddings with diverse question-answer tasks, including feature querying, comparison, and semantic description.<n>Our results demonstrate that treating embeddings as primary data inputs, provides a more direct, efficient, and scalable approach to multimodal geospatial intelligence.
  arXiv  Detail & Related papers  (2026-04-08T18:31:38Z)
• Concise Geometric Description as a Bridge: Unleashing the Potential of LLM for Plane Geometry Problem Solving [50.05273675575345]
  PlaneThought Problem Solving (PGPS) aims to solve a plane geometric problem based on a geometric diagram and problem textual descriptions.<n>Large Language Models (LLMs) possess strong reasoning skills, their direct application to PGPS is hindered by their inability to process visual diagrams.<n>We train a MLLM Interpreter to generate geometric descriptions for the visual diagram, and an off-the-shelf LLM is utilized to perform reasoning.
  arXiv  Detail & Related papers  (2026-01-29T02:03:33Z)
• Understanding the Geospatial Reasoning Capabilities of LLMs: A Trajectory Recovery Perspective [31.228269455751363]
  This paper explores whether Large Language Models (LLMs) can read road network maps and perform navigation.<n>We frame trajectory recovery as a proxy task, which requires models to reconstruct masked GPS traces.<n>Using road network as context, our prompting framework enables LLMs to generate valid paths without accessing any external navigation tools.
  arXiv  Detail & Related papers  (2025-10-02T03:37:41Z)
• DistRAG: Towards Distance-Based Spatial Reasoning in LLMs [1.1435139523855764]
  We develop a novel approach, DistRAG, that enables an LLM to retrieve relevant spatial information not explicitly learned during training.<n>Our method encodes the geodesic distances between cities and towns in a graph and retrieves a context subgraph relevant to the question.
  arXiv  Detail & Related papers  (2025-06-03T22:10:39Z)
• OmniGeo: Towards a Multimodal Large Language Models for Geospatial Artificial Intelligence [51.0456395687016]
  multimodal large language models (LLMs) have opened new frontiers in artificial intelligence.<n>We propose a MLLM (OmniGeo) tailored to geospatial applications.<n>By combining the strengths of natural language understanding and spatial reasoning, our model enhances the ability of instruction following and the accuracy of GeoAI systems.
  arXiv  Detail & Related papers  (2025-03-20T16:45:48Z)
• GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks [84.86699025256705]
  We present GEOBench-VLM, a benchmark specifically designed to evaluate Vision-Language Models (VLMs) on geospatial tasks.<n>Our benchmark features over 10,000 manually verified instructions and spanning diverse visual conditions, object types, and scales.<n>We evaluate several state-of-the-art VLMs to assess performance on geospatial-specific challenges.
  arXiv  Detail & Related papers  (2024-11-28T18:59:56Z)
• An LLM Agent for Automatic Geospatial Data Analysis [5.842462214442362]
  Large language models (LLMs) are being used in data science code generation tasks. Their application to geospatial data processing is challenging due to difficulties in incorporating complex data structures and spatial constraints. We introduce GeoAgent, a new interactive framework designed to help LLMs handle geospatial data processing more effectively.
  arXiv  Detail & Related papers  (2024-10-24T14:47:25Z)
• Swarm Intelligence in Geo-Localization: A Multi-Agent Large Vision-Language Model Collaborative Framework [51.26566634946208]
  We introduce smileGeo, a novel visual geo-localization framework. By inter-agent communication, smileGeo integrates the inherent knowledge of these agents with additional retrieved information. Results show that our approach significantly outperforms current state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-08-21T03:31:30Z)
• GeoLLM: Extracting Geospatial Knowledge from Large Language Models [49.20315582673223]
  We present GeoLLM, a novel method that can effectively extract geospatial knowledge from large language models. We demonstrate the utility of our approach across multiple tasks of central interest to the international community, including the measurement of population density and economic livelihoods. Our experiments reveal that LLMs are remarkably sample-efficient, rich in geospatial information, and robust across the globe.
  arXiv  Detail & Related papers  (2023-10-10T00:03:23Z)
• Are Large Language Models Geospatially Knowledgeable? [21.401931052512595]
  This paper investigates the extent of geospatial knowledge, awareness, and reasoning abilities encoded within Large Language Models (LLM) With a focus on autoregressive language models, we devise experimental approaches related to (i) probing LLMs for geo-coordinates to assess geospatial knowledge, (ii) using geospatial and non-geospatial prepositions to gauge their geospatial awareness, and (iii) utilizing a multidimensional scaling (MDS) experiment to assess the models' geospatial reasoning capabilities.
  arXiv  Detail & Related papers  (2023-10-09T17:20:11Z)
• K2: A Foundation Language Model for Geoscience Knowledge Understanding and Utilization [105.89544876731942]
  Large language models (LLMs) have achieved great success in general domains of natural language processing. We present the first-ever LLM in geoscience, K2, alongside a suite of resources developed to further promote LLM research within geoscience.
  arXiv  Detail & Related papers  (2023-06-08T09:29:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.