Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kuai, Chenchen, Li, Zihao, Rosen, Braden, Paal, Stephanie, Jafari, Navid, Briaud, Jean-Louis, Zhang, Yunlong, Hashash, Youssef M. A., Zhou, Yang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.14010
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917091734454272
author Kuai, Chenchen
Li, Zihao
Rosen, Braden
Paal, Stephanie
Jafari, Navid
Briaud, Jean-Louis
Zhang, Yunlong
Hashash, Youssef M. A.
Zhou, Yang
author_facet Kuai, Chenchen
Li, Zihao
Rosen, Braden
Paal, Stephanie
Jafari, Navid
Briaud, Jean-Louis
Zhang, Yunlong
Hashash, Youssef M. A.
Zhou, Yang
contents Post-disaster reconnaissance reports contain critical evidence for understanding multi-hazard interactions, yet their unstructured narratives make systematic knowledge transfer difficult. Large language models (LLMs) offer new potential for analyzing these reports, but often generate unreliable or hallucinated outputs when domain grounding is absent. This study introduces the Mixture-of-Retrieval Agentic RAG (MoRA-RAG), a knowledge-grounded LLM framework that transforms reconnaissance reports into a structured foundation for multi-hazard reasoning. The framework integrates a Mixture-of-Retrieval mechanism that dynamically routes queries across hazard-specific databases while using agentic chunking to preserve contextual coherence during retrieval. It also includes a verification loop that assesses evidence sufficiency, refines queries, and initiates targeted searches when information remains incomplete. We construct HazardRecQA by deriving question-answer pairs from GEER reconnaissance reports, which document 90 global events across seven major hazard types. MoRA-RAG achieves up to 94.5 percent accuracy, outperforming zero-shot LLMs by 30 percent and state-of-the-art RAG systems by 10 percent, while reducing hallucinations across diverse LLM architectures. MoRA-RAG also enables open-weight LLMs to achieve performance comparable to proprietary models. It establishes a new paradigm for transforming post-disaster documentation into actionable, trustworthy intelligence for hazard resilience.
format Preprint
id arxiv_https___arxiv_org_abs_2511_14010
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Knowledge-Grounded Agentic Large Language Models for Multi-Hazard Understanding from Reconnaissance Reports
Kuai, Chenchen
Li, Zihao
Rosen, Braden
Paal, Stephanie
Jafari, Navid
Briaud, Jean-Louis
Zhang, Yunlong
Hashash, Youssef M. A.
Zhou, Yang
Computation and Language
Artificial Intelligence
Post-disaster reconnaissance reports contain critical evidence for understanding multi-hazard interactions, yet their unstructured narratives make systematic knowledge transfer difficult. Large language models (LLMs) offer new potential for analyzing these reports, but often generate unreliable or hallucinated outputs when domain grounding is absent. This study introduces the Mixture-of-Retrieval Agentic RAG (MoRA-RAG), a knowledge-grounded LLM framework that transforms reconnaissance reports into a structured foundation for multi-hazard reasoning. The framework integrates a Mixture-of-Retrieval mechanism that dynamically routes queries across hazard-specific databases while using agentic chunking to preserve contextual coherence during retrieval. It also includes a verification loop that assesses evidence sufficiency, refines queries, and initiates targeted searches when information remains incomplete. We construct HazardRecQA by deriving question-answer pairs from GEER reconnaissance reports, which document 90 global events across seven major hazard types. MoRA-RAG achieves up to 94.5 percent accuracy, outperforming zero-shot LLMs by 30 percent and state-of-the-art RAG systems by 10 percent, while reducing hallucinations across diverse LLM architectures. MoRA-RAG also enables open-weight LLMs to achieve performance comparable to proprietary models. It establishes a new paradigm for transforming post-disaster documentation into actionable, trustworthy intelligence for hazard resilience.
title Knowledge-Grounded Agentic Large Language Models for Multi-Hazard Understanding from Reconnaissance Reports
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2511.14010