用知识图谱增强对话系统，帮无家可归者精准获取社区服务信息。
DreamKG: A KG-Augmented Conversational System for People Experiencing Homelessness
- 结合知识图谱与大模型，用结构化查询确保回答准确可靠。
- 在相关查询上比谷歌AI搜索高59%准确率，84%无关请求被拒。
- 适合需要实时、可信本地服务信息的弱势群体使用。
无家可归者（PEH）在获取及时、准确的社区服务信息方面面临巨大障碍。DreamKG通过一个基于知识图谱的对话系统解决此问题，将回应建立在对费城组织、服务、位置和营业时间的经验证据基础上。与容易产生幻觉的标准大语言模型（LLMs）不同，DreamKG结合了Neo4j知识图谱与结构化查询理解，可靠地处理位置敏感和时间相关的查询。系统具备空间推理能力以进行距离推荐，并支持时间过滤以匹配营业时间。初步评估显示，在相关查询上比谷歌搜索AI高出59%的准确性，且84%的无关查询被有效拒绝。该演示表明，混合架构——融合大模型灵活性与知识图谱可靠性——能有效提升弱势群体的服务可及性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。