Verifiable Disaster Storylines and Causal Knowledge Graphs: A Citation-Grounded Pipeline from Heterogeneous Humanitarian Sources
cs.AI, cs.CL
Submitted: 2026-09-01
Updated: 2026-09-13
Journal ref: International Conference on Information Technology for Social Good (GoodIT '26), September 02--04, 2026, Pisa, Italy
Code: https://github.com/idecost/StoryLine_KG
Project page: https://idecost.github.io/StoryLine_
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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
Terminology
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 new collection of disaster stories complementing the EM-DAT database.
Sources
- FloodBrain: Flood Disaster Reporting by Web-based Retrieval Augmented Generation with an LLM
- A Large-Language-Model Framework for Automated Humanitarian Situation Reporting
- The Llama 3 Herd of Models
- Knowledge Graph Validation
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
- Evaluating Retrieval Quality in Retrieval-Augmented Generation
- Attribute First, then Generate: Locally-attributable Grounded Text Generation
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems