Verifiable Disaster Storylines and Causal Knowledge Graphs: A Citation-Grounded Pipeline from Heterogeneous Humanitarian Sources

• URL: http://arxiv.org/abs/2609.00858v1
• Date: Tue, 01 Sep 2026 07:56:12 GMT
• Title: Verifiable Disaster Storylines and Causal Knowledge Graphs: A Citation-Grounded Pipeline from Heterogeneous Humanitarian Sources
• Abstract summary: We present a pipeline that combines structured disaster records with unstructured documents to produce source-grounded disaster storylines and causal knowledge graphs.<n>We evaluate the system on three diverse crisis use cases through a human evaluation involving 9 domain expert and 9 non-expert evaluators.<n>Results confirm high retrieval precision, strong faithfulness of extracted causal relations, and a clear expert preference for citation-grounded components over ungrounded alternatives.
• Score: 1.561704911463062
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Effective humanitarian response depends on the rapid synthesis of heterogeneous, high-volume information sources - a task that routinely exceeds human analytical capacity in the critical early hours of a crisis. We present a pipeline that combines structured disaster records from EM-DAT with unstructured documents from ReliefWeb and the European Media Monitor (EMM) to produce source-grounded disaster storylines and causal knowledge graphs supporting situational awareness for responders and analysts. Using Retrieval-Augmented Generation, the pipeline extracts structured storylines - tabular event profiles covering 17 fields, from severity and key drivers to child-sensitive impact indicators - and constructs causal knowledge graphs where each node and edge is enriched with citation-grounded explanatory narratives, enabling full traceability back to primary sources. We evaluate the system on three diverse crisis use cases through a human evaluation involving 9 domain expert and 9 non-expert evaluators. Results confirm high retrieval precision, strong faithfulness of extracted causal relations, and a clear expert preference for citation-grounded components over ungrounded alternatives. The pipeline is designed to scale to the full EM-DAT catalogue, with the goal of publicly releasing a narrative-enriched version of the database.

Related papers

• WILDTRACE: Benchmarking Natural Evidence Trails in Long-Context Reasoning [63.9071746889252]
  Answering complex questions over long documents frequently requires integrating evidence that the source itself disperses naturally across distant passages.<n>This source-internal evidence integration is central to real-world long-document analysis, yet existing benchmarks largely sidestep it.<n>We introduce WILDTRACE, a benchmark of 481 tasks over 214 naturally occurring long-form sources.
  arXiv  Detail & Related papers  (2026-07-10T12:09:21Z)
• Can LLM Agents Respond to Disasters? Benchmarking Heterogeneous Geospatial Reasoning in Emergency Operations [55.251494694783894]
  Disaster Operational Response Agent benchmark (DORA) is the first agentic benchmark for end-to-end disaster response.<n>Tasks span five dimensions that cover the operational disaster-response pipeline: disaster perception, spatial relational analysis, rescue and evacuation planning, temporal evolution reasoning, and multi-modal report synthesis.<n>DORA establishes a rigorous testbed for operationally reliable disaster-response agents.
  arXiv  Detail & Related papers  (2026-05-12T06:57:41Z)
• Large Language Models for Causal Relations Extraction in Social Media: A Validation Framework for Disaster Intelligence [10.83315119677514]
  We examine whether Large Language Models (LLMs) can effectively extract causal relations from disaster-related social media posts.<n>Our findings highlight both the potential and risks of using LLMs for causal relation extraction in disaster decision-support systems.
  arXiv  Detail & Related papers  (2026-05-12T00:07:45Z)
• RAPTOR-AI for Disaster OODA Loop: Hierarchical Multimodal RAG with Experience-Driven Agentic Decision-Making [0.0]
  This work introduces an agentic Retrieval-Augmented Generation framework designed to support the three canonical phases of disaster response: initial rescue, mid-term recovery, and long-term reconstruction.<n>To achieve robust multimodal grounding, we construct a hierarchical knowledge base that integrates textual disaster manuals, historical lessons, and aerial and ground-level imagery.<n>Our system builds on the open-source multimodal implementation, which processes 46 tsunami-related PDFs (2,378 pages) using BLIP-based image captioning, ColVBERT embeddings, and long-context summarization.
  arXiv  Detail & Related papers  (2026-01-18T10:58:41Z)
• WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research [73.58638285105971]
  This paper tackles textbfopen-ended deep research (OEDR), a complex challenge where AI agents must synthesize vast web-scale information into insightful reports.<n>We introduce textbfWebWeaver, a novel dual-agent framework that emulates the human research process.<n>Our framework establishes a new state-of-the-art across major OEDR benchmarks, including DeepResearch Bench, DeepConsult, and DeepResearchGym.
  arXiv  Detail & Related papers  (2025-09-16T17:57:21Z)
• Benchmarking Deep Search over Heterogeneous Enterprise Data [73.55304268238474]
  We present a new benchmark for evaluating a form of retrieval-augmented generation (RAG)<n>RAG requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources.<n>We build it using a synthetic data pipeline that simulates business across product planning, development, and support stages.
  arXiv  Detail & Related papers  (2025-06-29T08:34:59Z)
• Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents [64.43980129731587]
  We propose a causal-inspired inference-time debiasing method called Causal Diagnosis and Correction (CDC)<n>CDC first diagnoses the bias effect of the perplexity and then separates the bias effect from the overall relevance score.<n> Experimental results across three domains demonstrate the superior debiasing effectiveness.
  arXiv  Detail & Related papers  (2025-03-11T17:59:00Z)
• Data Taxonomy Towards the Applicability of the Digital Twin Conceptual Framework in Disaster Management [0.562479170374811]
  The Digital Twin (DT) offers a novel approach to the management of critical infrastructures.<n>The increasing complexity and interconnectedness of these infrastructures necessitate the development of robust disaster response and management strategies.<n>This research introduces a taxonomy and similarity function for comparing data sources based on their features and vulnerability to crisis events.
  arXiv  Detail & Related papers  (2025-02-27T21:08:03Z)
• Causality Extraction from Nuclear Licensee Event Reports Using a Hybrid Framework [3.1139106894905972]
  This paper proposed a hybrid framework for causality detection and extraction from nuclear licensee event reports. We compiled an LER corpus with 20,129 text samples for causality analysis, developed an interactive tool for labeling cause effect pairs, and built a deep-learning-based approach for causal relation detection.
  arXiv  Detail & Related papers  (2024-04-08T16:39:34Z)
• Multi-modal Causal Structure Learning and Root Cause Analysis [67.67578590390907]
  We propose Mulan, a unified multi-modal causal structure learning method for root cause localization. We leverage a log-tailored language model to facilitate log representation learning, converting log sequences into time-series data. We also introduce a novel key performance indicator-aware attention mechanism for assessing modality reliability and co-learning a final causal graph.
  arXiv  Detail & Related papers  (2024-02-04T05:50:38Z)
• FloodBrain: Flood Disaster Reporting by Web-based Retrieval Augmented Generation with an LLM [0.9374652839580183]
  We introduce a sophisticated pipeline embodied in our tool FloodBrain (floodbrain.com) Our pipeline assimilates information from web search results to produce detailed and accurate reports on flood events. We find a notable correlation between the scores assigned by GPT-4 and the scores given by human evaluators when comparing our generated reports to human-authored ones.
  arXiv  Detail & Related papers  (2023-11-05T08:34:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.