DreamKG: A KG-Augmented Conversational System for People Experiencing Homelessness

TL;DR

DreamKG is a hybrid knowledge graph and LLM-based conversational system designed to provide accurate, location-aware, and time-sensitive information to people experiencing homelessness, outperforming standard search AI in relevant queries.

Contribution

This work introduces a novel hybrid system combining Neo4j knowledge graphs with LLMs to improve information accuracy and reliability for vulnerable populations.

Findings

Achieved 59% superiority over Google Search AI on relevant queries.

84% rejection rate of irrelevant queries.

Effectively handles spatial reasoning and temporal filtering.

Abstract

People experiencing homelessness (PEH) face substantial barriers to accessing timely, accurate information about community services. DreamKG addresses this through a knowledge graph-augmented conversational system that grounds responses in verified, up-to-date data about Philadelphia organizations, services, locations, and hours. Unlike standard large language models (LLMs) prone to hallucinations, DreamKG combines Neo4j knowledge graphs with structured query understanding to handle location-aware and time-sensitive queries reliably. The system performs spatial reasoning for distance-based recommendations and temporal filtering for operating hours. Preliminary evaluation shows 59% superiority over Google Search AI on relevant queries and 84% rejection of irrelevant queries. This demonstration highlights the potential of hybrid architectures that combines LLM flexibility with knowledge graph reliability to improve service accessibility for vulnerable populations effectively.