Conference
Open access
Aug 2026
Causal Evidence Extraction and Triangulation in Crisis Reports using Large Language Models: A ReliefWeb-based Study
A ReliefWeb study (2000-2024) and a two-stage Large Language Model (LLM) pipeline that extracts structured intervention-outcome records with direction and strength attributes and proposes context-preserving triangulation that aggregates strength-weighted evidence within disaster cells.
Yuanjun Zhang, Mourad Oussalah
· Annual Meeting of the Associ... · 0 citations