DisastRAG: A Multi-Source Disaster Information Integration and Access System Based on Retrieval-Augmented Large Language Models

2026-04-06

AI Summary

This study addresses the limitations of existing disaster information systems, which often rely on a single information source and struggle to meet the demands of heterogeneous, time-sensitive, and context-dependent data. To overcome these challenges, this work proposes a disaster-aware multi-source information fusion architecture that, for the first time, integrates structured database querying with a dynamic web fallback mechanism into a retrieval-augmented generation (RAG) framework, thereby transcending traditional single-channel constraints. The system enables coordinated multi-path responses through query understanding, policy-based routing, hybrid retrieval (combining vector search and re-ranking), and contextual memory. Experimental results demonstrate substantial improvements: accuracy in multiple-choice tasks increases by 12–23 percentage points, and key-point coverage in open-ended question answering rises by up to 10.5%, with particularly pronounced gains for weaker language models. The findings also highlight the necessity for stronger models to effectively suppress retrieval-induced noise.

Abstract

Effective disaster management requires rapid access to information distributed across structured operational records, unstructured institutional documents, and dynamic external sources. However, most existing disaster information systems and retrieval-augmented generation frameworks remain organized around a single access pathway, limiting their ability to support heterogeneous, time-sensitive, and context-dependent information needs. This study presents DisastRAG, a disaster-aware information integration and access system that combines large language models with retrieval-augmented access to structured, unstructured, and contextual disaster information. The framework is built around a multi-path architecture that supports document retrieval over a curated hazard corpus, structured access over relational disaster records, and external web fallback for out-of-corpus requests, while also incorporating query understanding, strategy routing, response generation, and contextual memory within a unified system. We evaluated the document retrieval performance using four open-source large language models across multiple retrieval configurations on multiple-choice and open-ended disaster information tasks. Retrieval augmentation consistently improves performance over no-retrieval baselines, yielding multiple-choice gains of 12-23 percentage points and open-ended keypoint coverage gains of up to 10.5 percentage points. Results show that larger candidate pools are most helpful for weaker models, while stronger models are more sensitive to retrieval noise. Hybrid retrieval performs best for open-ended coverage, whereas vector retrieval and shallower reranking more often favor closed-form factual selection. Case studies further show that structured access and web fallback extend the framework beyond document-only RAG.

Problem

• disaster information integration
• retrieval-augmented generation
• multi-source access
• heterogeneous information
• time-sensitive retrieval

Innovation

• Retrieval-Augmented Generation
• Multi-Source Information Integration
• Disaster Management
• Large Language Models
• Hybrid Retrieval