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

2026-04-13

AI Summary

This work addresses the challenge faced by unhoused individuals in accessing timely and accurate local service information. The authors propose a dialogue system that integrates a knowledge graph with a large language model, leveraging authoritative service data from Philadelphia to enable location-aware and operating-hours-sensitive service recommendations through structured query understanding. By combining the flexibility of large language models with the reliability of knowledge graphs, the system effectively mitigates hallucinations while supporting spatial reasoning and temporal filtering. Experimental results demonstrate that the system outperforms Google Search AI by 59% on relevant queries and correctly rejects 84% of irrelevant questions, significantly enhancing service accessibility for vulnerable populations.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: Conversational AI/Dialog Systems

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• homelessness
• information access
• community services
• vulnerable populations
• service accessibility

Innovation

• knowledge graph
• conversational system
• hallucination mitigation
• spatial reasoning
• temporal filtering