LLMs as World Models: Data-Driven and Human-Centered Pre-Event Simulation for Disaster Impact Assessment
Published in Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), 2025
Recommended citation: Li, L., Li, D., Ou, Z., Xu, X., Liu, J., Ma, Z., Yu, R., & Deng, M. (2025). LLMs as World Models: Data-Driven and Human-Centered Pre-Event Simulation for Disaster Impact Assessment. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025). https://doi.org/10.18653/v1/2025.emnlp-main.153.
A human-centered world-model framework uses LLMs to simulate pre-event disaster impacts and support anticipatory assessment.