aiqbench analysis
This research introduces a Retrieval-Augmented Generation pipeline that synthesizes heterogeneous humanitarian data into citation-grounded causal knowledge graphs for disaster response. By enforcing traceability back to primary sources like EM-DAT and ReliefWeb, the system addresses critical needs for situational awareness where hallucination-free analysis is paramount. The approach demonstrates high precision in extracting structured event profiles and causal relations, offering a scalable solution for augmenting human analytical capacity during crises.
Verifiable Disaster Storylines and Causal Knowledge Graphs: A Citation-Grounded Pipeline from Heterogeneous Humanitarian Sources
arXiv:2609.00858v1 Announce Type: new 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.
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.
Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
arXiv:2609.00858 [cs.AI]
(or arXiv:2609.00858v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.00858 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
https://doi.org/10.1145/3794786.3830759 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 291 words
Related coverage
Narrative Knowledge Weaver: Narrative-Centric Retrieval-Augmented Reasoning for Long-Form Text Understanding
arXiv · Jun 6, 2026
SciR: A Controllable Benchmark for Scientific Reasoning in LLMs
arXiv · Jun 12, 2026
Microsoft’s AI chief says superintelligence is near, but won’t take your job
The Verge · Jun 8, 2026
Implicit Causal Graph Construction in Text via Chain Discovery
arXiv · Jun 9, 2026