mlsanityData to 14 Oct 2026

Quantifying Geospatial in the Common Crawl Corpus

arXiv 2406.04952 ↗First posted 7 Jun 2024cs.CL cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) exhibit emerging geospatial capabilities, stemming from their pre-training on vast unlabelled text datasets that are often derived from the Common Crawl (CC) corpus. However, the geospatial content within CC remains largely unexplored, impacting our understanding of LLMs' spatial reasoning. This paper investigates the prevalence of geospatial data in recent Common Crawl releases using Gemini 1.5, a powerful language model. By analyzing a sample of documents and manually revising the results, we estimate that 18.7% of web documents in CC contain geospatial information such as coordinates and addresses. We find little difference in prevalence between Enlgish- and non-English-language documents. Our findings provide quantitative insights into the nature and extent of geospatial data in CC, and lay the groundwork for future studies of geospatial biases of LLMs.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 11 of its 32 references that are in the map. First posted on arXiv 7 Jun 2024.

Builds on

11 of 32 references.

References · 11

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  3. 2021Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpuscited by 492
  4. 2021Multimodal datasets: misogyny, pornography, and malignant stereotypescited by 327
  5. 2021Quality at a Glance: An Audit of Web-Crawled Multilingual Datasetscited by 243
  6. 2024Large Language Models are Geographically Biasedcited by 93
  7. 2023On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligencecited by 88
  8. 2023Empirical Study of Zero-Shot NER with ChatGPTcited by 60
  9. 2023Are Large Language Models Geospatially Knowledgeable?cited by 30
  10. 2022'I think I discovered a military base in the middle of the ocean' -- Null Island, the most real of fictional placescited by 2
  11. 2024CC-GPX: Extracting High-Quality Annotated Geospatial Data from Common Crawlcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Understanding the Geospatial Reasoning Capabilities of LLMs: A Trajectory Recovery Perspectivecited by 1
  2. 2026The Scenic Route to Deception: Dark Patterns and Explainability Pitfalls in Conversational Navigationcited by 1
  3. 2025Coordinates from Context: Using LLMs to Ground Complex Location Referencescited by 0
  4. 2026Much of Geospatial Web Search Is Beyond Traditional GIScited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Geospatial Mechanistic Interpretability of Large Language Models
  2. 2023GeoLM: Empowering Language Models for Geospatially Grounded Language Understanding
  3. 2026Exploring Geographic Relative Space in Large Language Models through Activation Patching
  4. 2024Can Large Language Models Generate Geospatial Code?
  5. 2024GeoReasoner: Reasoning On Geospatially Grounded Context For Natural Language Understanding
  6. 2025GeoAnalystBench: A GeoAI benchmark for assessing large language models for spatial analysis workflow and code generation
  7. 2025Can Large Language Models Integrate Spatial Data? Empirical Insights into Reasoning Strengths and Computational Weaknesses
  8. 2025Mitigating Geospatial Knowledge Hallucination in Large Language Models: Benchmarking and Dynamic Factuality Aligning