DreamKG: A KG-Augmented Conversational System for People Experiencing Homelessness
This work addresses the critical need for reliable information access for a vulnerable population, demonstrating a practical application of hybrid LLM-KG architectures.
DreamKG is a knowledge graph-augmented conversational system that helps people experiencing homelessness access accurate information about community services. It achieves 59% superiority over Google Search AI on relevant queries and 84% rejection of irrelevant queries.
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.