What Will Happen Next: Large Models-Driven Deduction for Emergency Instances

2026-05-08

AI Summary

Traditional emergency simulation methods often fail to adequately uncover the latent risks of rare emergency events due to their limited randomness and diversity. To address this, this work proposes a large model–driven World-Line Divergence System (WLDS), which, for the first time, leverages large language models for multi-path emergency scenario reasoning. The system incorporates dynamic generation, a dual verification mechanism based on factual accuracy and logical consistency, and interactive user-guided path selection to effectively mitigate hallucinations while ensuring rigor and fidelity in simulations. Enhanced with multimodal visualizations for improved interpretability, WLDS achieves high-precision, high-fidelity emergency scenario generation across multiple domains on a newly curated EID benchmark dataset, significantly advancing decision support capabilities and data generation efficiency.

Abstract

Traditional simulation methods reproduce occurred emergency instances through presetting to assist people in risk assessment and emergency decision-making. However, due to the lack of randomness and diversity, existing simulation systems struggle to fully explore the potential risk as emergency instances are scarce. In contrast, Large Models (LMs) can dynamically adjust generation strategies to introduce controllable randomness, while also possessing extensive prior knowledge and cross-domain knowledge transfer capabilities. Inspired by it, we propose the LMs-driven World Line Divergence System (WLDS), which enables diversified visualization and deduction of emergency instances in different domains. WLDS leverages LMs to deduce emergency instances in various development directions, and introduces the factual calibration and logical calibration mechanism to ensure factual accuracy and logical rigor during the deduction process. The interactive module can independently select deduction directions to avoid potential hallucinations that are difficult for the system to identify. Furthermore, by introducing the visualization module, WLDS forms simulation and deduction that combine text and images, which enhances interpretability. Extensive experiments conducted on the proposed Emergency Instances Deduction (EID) benchmark dataset demonstrate that WLDS achieves high-precision and high-fidelity simulation and deduction of emergency instances in multiple specific domains. Relevant experiments further demonstrate that WLDS can generate more emergency instances deduction data for users and provide support for better decision-making in similar emergency instances in the future.

Problem

• emergency instances
• simulation
• risk assessment
• decision-making
• diversity

Innovation

• Large Models
• World Line Divergence System
• Emergency Instance Deduction
• Factual and Logical Calibration
• Multimodal Visualization