Harnessing AI Agents to Advance Research on Refugee Child Mental Health

TL;DR

This paper develops and compares two AI-based retrieval-augmented generation pipelines to process refugee health data, aiming to improve mental health insights for displaced children and support humanitarian efforts.

Contribution

It introduces a scalable AI framework combining RAG methods with migration and child psychology research, demonstrating improved accuracy in processing challenging datasets.

Findings

DeepSeek R1-7B outperforms Zephyr-7B-beta with 0.91 relevance accuracy.

Both models function properly on humanitarian datasets.

The approach aids policymakers and practitioners in mental health assessment.

Abstract

The international refugee crisis deepens, exposing millions of dis placed children to extreme psychological trauma. This research suggests a com pact, AI-based framework for processing unstructured refugee health data and distilling knowledge on child mental health. We compare two Retrieval-Aug mented Generation (RAG) pipelines, Zephyr-7B-beta and DeepSeek R1-7B, to determine how well they process challenging humanitarian datasets while avoid ing hallucination hazards. By combining cutting-edge AI methods with migration research and child psychology, this study presents a scalable strategy to assist policymakers, mental health practitioners, and humanitarian agencies to better assist displaced children and recognize their mental wellbeing. In total, both the models worked properly but significantly Deepseek R1 is superior to Zephyr with an accuracy of answer relevance 0.91