LLM Memory & RAG 相关度: 8/10

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

Javad M Alizadeh, Genhui Zheng, Chiu C Tan, Yuzhou Chen, Omar Martinez, Philip McCallion, Ying Ding, Chenguang Yang, AnneMarie Tomosky, Huanmei Wu
arXiv: 2604.11703v1 发布: 2026-04-13 更新: 2026-04-13
下载 PDF arXiv 页面

AI 摘要

DreamKG利用知识图谱增强对话系统，为无家可归者提供准确的社区服务信息。

主要贡献

  • 构建了面向无家可归者的知识图谱增强对话系统DreamKG
  • 结合Neo4j知识图谱和LLM，提高了信息准确性和可靠性
  • 实现了基于位置和时间的社区服务推荐

方法论

利用Neo4j知识图谱存储社区服务信息，LLM用于对话理解，结合空间和时间推理进行服务推荐。

原文摘要

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.

标签

知识图谱 对话系统 自然语言处理 社区服务 LLM

arXiv 分类

cs.AI