Tag
This paper presents a two-stage LLM pipeline for extracting and triangulating causal evidence from humanitarian crisis reports, achieving strong F1 scores on a ReliefWeb dataset and proposing a Level-of-Evidence score for cross-context convergence.
A company is developing humanitarian missiles to deliver supplies to climbers stranded on Mount Everest, as suggested by Ryan Petersen.
The UN AI for Good Summit showcased AI applications like robot dogs and Teslas, while sparking debates on AI ethics, corporate overreach, and the gap between hype and practical deployment.
This benchmark study evaluates 46 large language models against human experts for coding qualitative humanitarian data, finding that LLMs can achieve comparable reliability with structured prompts and reasoning, but require careful oversight for nuanced themes.
In Gaza, a project called Green Rock recycles rubble from destroyed buildings into Lego-like interlocking bricks to address the shortage of construction materials, providing an affordable and locally produced building solution.