mlsanityData to 14 Oct 2026

LLMs as World Models: Data-Driven and Human-Centered Pre-Event Simulation for Disaster Impact Assessment

arXiv 2506.06355 ↗First posted 2 Jun 2025cs.CY cs.CE cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Efficient simulation is essential for enhancing proactive preparedness for sudden-onset disasters such as earthquakes. Recent advancements in large language models (LLMs) as world models show promise in simulating complex scenarios. This study examines multiple LLMs to proactively estimate perceived earthquake impacts. Leveraging multimodal datasets including geospatial, socioeconomic, building, and street-level imagery data, our framework generates Modified Mercalli Intensity (MMI) predictions at zip code and county scales. Evaluations on the 2014 Napa and 2019 Ridgecrest earthquakes using USGS ''Did You Feel It? (DYFI)'' reports demonstrate significant alignment, as evidenced by a high correlation of 0.88 and a low RMSE of 0.77 as compared to real reports at the zip code level. Techniques such as RAG and ICL can improve simulation performance, while visual inputs notably enhance accuracy compared to structured numerical data alone. These findings show the promise of LLMs in simulating disaster impacts that can help strengthen pre-event planning.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 21 of its 62 references that are in the map. First posted on arXiv 2 Jun 2025.

Builds on

21 of 62 references.

References · 21

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2023Reasoning with Language Model is Planning with World Modelcited by 861
  4. 2022A Survey on In-context Learningcited by 721
  5. 2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 494
  6. 2023Large Language Models as Commonsense Knowledge for Large-Scale Task Planningcited by 231
  7. 2024Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agentscited by 154
  8. 2023Language Models Meet World Models: Embodied Experiences Enhance Language Modelscited by 124
  9. 2023From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thoughtcited by 119
  10. 2024"Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Modelscited by 60
  11. 2024LLM Processes: Numerical Predictive Distributions Conditioned on Natural Languagecited by 55
  12. 2025TimeCAP: Learning to Contextualize, Augment, and Predict Time Series Events with Large Language Model Agentscited by 37
9 more
  1. 2024OpenCity: A Scalable Platform to Simulate Urban Activities with Massive LLM Agentscited by 35
  2. 2025Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspectivecited by 29
  3. 2024Exploring Large Language Models for Feature Selection: A Data-centric Perspectivecited by 27
  4. 2024LLM-Assisted Crisis Management: Building Advanced LLM Platforms for Effective Emergency Response and Public Collaborationcited by 21
  5. 2024When Raw Data Prevails: Are Large Language Model Embeddings Effective in Numerical Data Representation for Medical Machine Learning Applications?cited by 12
  6. 2025Unveiling Challenges for LLMs in Enterprise Data Engineeringcited by 9
  7. 2024LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulationcited by 8
  8. 2024Large Language Models in Fire Engineering: An Examination of Technical Questions Against Domain Knowledgecited by 5
  9. 2024Automated Floodwater Depth Estimation Using Large Multimodal Model for Rapid Flood Mappingcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 3.

6 papers.

  1. 2025From Word to World: Can Large Language Models be Implicit Text-based World Models?cited by 42
  2. 2025From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Modelscited by 12
  3. 2026Bridging the Agent-World Gap: Text World Models for LLM-based Agentscited by 5
  4. 2025CyPortQA: Benchmarking Multimodal Large Language Models for Cyclone Preparedness in Port Operationcited by 3
  5. 2026Do VLMs See What Sensors Feel? A Scalable Expert-Guided Design for Wheelchair Accessibility Assessment from Street Viewcited by 1
  6. 2026An Agentic Interface for End-to-End Probabilistic Seismic Hazard and Risk Analysiscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Multimodal, Multilingual, and Multidimensional Pipeline for Fine-grained Crowdsourcing Earthquake Damage Evaluation
  2. 2026Can Large Language Models Revolutionize Survey Research? Experiments with Disaster Preparedness Responses
  3. 2023FloodBrain: Flood Disaster Reporting by Web-based Retrieval Augmented Generation with an LLM
  4. 2026A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challenges
  5. 2024Leveraging LLMs for MT in Crisis Scenarios: a blueprint for low-resource languages
  6. 2025Prompt to Protection: A Comparative Study of Multimodal LLMs in Construction Hazard Recognition
  7. 2026Empirical Grounding Improves the Realism of LLM Agents Simulating Human Behavior During Disruptions
  8. 2025What Makes LLM Agent Simulations Useful for Policy Practice? An Iterative Design Study in Emergency Preparedness