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

cs.AIApr 13, 2026

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

Authors: Javad M Alizadeh, Genhui Zheng, Chiu C Tan, Yuzhou Chen, Omar Martinez, Philip McCallion, Ying Ding, Chenguang Yang,

Organizations: Temple University, Philadelphia, USA · University of Texas at Austin, Austin, USA · University of California Riverside, Riverside, USA · University of Central Florida, Florida, USA

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.

Geospatial QA

See all 17 papers

PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents
May 13, 2026Mikhail Menschikov, Matvey Iskornev, Alexander Kharitonov +8Multi-Hop QA Graph Retrieval-Augmented Generation
Skoltech, Moscow, Russia · SberAI, Moscow, Russia · Huawei, Moscow, Russia +4
RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question Answering
Mar 20, 2026Bo Yuan, Hexuan Deng, Xuebo Liu +1Knowledge Graph Question Answering LLM Reasoning with Graphs
Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China · Zhongguancun Academy, Beijing, China
UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG
Jan 28, 2026Dobrik Georgiev, Kheeran K. Naidu, Alberto Cattaneo +3Multi-Hop QA LLM Reasoning with Graphs
Graphcore Research

May 13, 2026J/K move · Enter open · S save

PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents

Mikhail Menschikov, Matvey Iskornev, Alexander Kharitonov, Alina Bogdanova+7

Skoltech, Moscow, Russia · SberAI, Moscow, Russia · Huawei, Moscow, Russia+4

Multi-Hop QA Graph Retrieval-Augmented Generation LLM Agents Knowledge Graph Question Answering

Open paper AskPDF arXiv

We introduce PersonalAI 2.0 (PAI-2), a novel framework designed to enhance LLM-based systems through integration of external knowledge graphs (KGs). The proposed approach addresses key limitations of existing Graph Retrieval-Augmented Generation (GraphRAG) methods by incorporating a dynamic, multistage query-processing pipeline. The central point of the PAI-2 design is its ability to perform adaptive, iterative information search, guided by extracted entities, matched graph vertices, and generated clue-queries. An evaluation conducted on five benchmarks (Natural Questions, TriviaQA, HotpotQA, 2WikiMultihopQA, and MuSiQue) demonstrates an improvement in the factual correctness of generated answers compared to analogue methods (LightRAG, RAPTOR, HippoRAG 2, and PAI-1). PAI-2 achieves a 9% average gain by LLM-as-a-Judge on the 2WikiMultihopQA and MuSiQue benchmarks, and attains accuracy comparable to HippoRAG 2 on the TriviaQA and HotpotQA benchmarks, reflecting its effectiveness in reducing hallucination rates and increasing precision. We show that enabled search plan enhancement mechanism gain 18% boost compared to disabled one by LLM-as-a-Judge across five benchmarks. In addition, an ablation study reveals that PAI-2 achieves SOTA result on the MINE-1 benchmark, obtaining an 89% information-retention score with LLMs in the 7--15B tiers. Collectively, these findings underscore the potential of PAI-2 to serve as a reusable component for personalized AI applications, which require scalable, context-aware knowledge-representation and reasoning capabilities. The source code of PAI-2 is available at the following link: https://github.com/Dzigen/PersonalAI.

Abstract

Geospatial QA

Explore similar work

PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents

RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question Answering

UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG