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

• URL: http://arxiv.org/abs/2604.11703v1
• Date: Mon, 13 Apr 2026 16:38:36 GMT
• Title: DreamKG: A KG-Augmented Conversational System for People Experiencing Homelessness
• Abstract summary: People experiencing homelessness face substantial barriers to accessing timely, accurate information about community services.<n>DreamKG addresses this through a knowledge graph-augmented conversational system that grounds responses in verified, up-to-date data.<n>Preliminary evaluation shows 59% superiority over Google Search AI on relevant queries and 84% rejection of irrelevant queries.
• Score: 25.758279348968625
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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.

Related papers

• Detecting Hallucinations for Large Language Model-based Knowledge Graph Reasoning [48.237729567730696]
  We propose LUCID, the first halLUcination deteCtIon method for LLM-based knowleDge graph reasoning frameworks.<n> LUCID jointly leverages LLM attention scores, KG semantics, and structural information.<n> Experiments on nine datasets show that LUCID achieves state of the art performance compared to 15 baselines.
  arXiv  Detail & Related papers  (2026-04-27T12:20:28Z)
• GISA: A Benchmark for General Information-Seeking Assistant [102.30831921333755]
  GISA is a benchmark for General Information-Seeking Assistants comprising 373 human-crafted queries.<n>It integrates both deep reasoning and broad information aggregation within unified tasks, and includes a live subset with periodically updated answers to resist memorization.<n>Experiments on mainstream LLMs and commercial search products reveal that even the best-performing model achieves only 19.30% exact match score.
  arXiv  Detail & Related papers  (2026-02-09T11:44:15Z)
• AskNearby: An LLM-Based Application for Neighborhood Information Retrieval and Personalized Cognitive-Map Recommendations [17.591012444861786]
  "15-minute city" envisions neighborhoods where residents can meet daily needs via a short walk or bike ride. Realizing this vision requires not only physical proximity but also efficient and reliable access to information about nearby places, services, and events.<n>We conceptualize this gap as the Local Life Information Accessibility (LLIA) problem and introduce AskNearby, an AI-driven community application.
  arXiv  Detail & Related papers  (2025-12-02T07:47:31Z)
• AI Knowledge Assist: An Automated Approach for the Creation of Knowledge Bases for Conversational AI Agents [11.61613387404681]
  A company-specific knowledge base is a major barrier to the integration of conversational AI systems in contact centers.<n>We introduce AI Knowledge Assist, a system that extracts knowledge in the form of question-answer (QA) pairs from historical customer-agent conversations to automatically build a knowledge base.
  arXiv  Detail & Related papers  (2025-10-09T12:34:31Z)
• Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking [63.84117489519164]
  Knowledge Graph Question Answering systems rely on high-quality benchmarks to evaluate complex multi-hop reasoning.<n>Despite their widespread use, popular datasets such as WebQSP and CWQ suffer from critical quality issues.<n>We introduce KGQAGen, an LLM-in-the-loop framework that systematically resolves these pitfalls.<n>Our findings advocate for more rigorous benchmark construction and position KGQAGen as a scalable framework for advancing KGQA evaluation.
  arXiv  Detail & Related papers  (2025-05-29T14:44:52Z)
• Mitigating LLM Hallucinations with Knowledge Graphs: A Case Study [2.40997250653065]
  LinkQ is an open-source natural language interface developed to combat hallucinations by forcing an LLM to query a knowledge graph for ground-truth data during question-answering (QA)<n>We conduct a quantitative evaluation of LinkQ using a well-known KGQA dataset, showing that the system outperforms GPT-4 but still struggles with certain question categories.<n>We discuss a qualitative study of LinkQ with two domain experts using a real-world cybersecurity KG, outlining these experts' feedback, suggestions, perceived limitations, and future opportunities for systems like LinkQ.
  arXiv  Detail & Related papers  (2025-04-16T18:40:01Z)
• Question-Aware Knowledge Graph Prompting for Enhancing Large Language Models [51.47994645529258]
  We propose Question-Aware Knowledge Graph Prompting (QAP), which incorporates question embeddings into GNN aggregation to dynamically assess KG relevance.<n> Experimental results demonstrate that QAP outperforms state-of-the-art methods across multiple datasets, highlighting its effectiveness.
  arXiv  Detail & Related papers  (2025-03-30T17:09:11Z)
• Transit Pulse: Utilizing Social Media as a Source for Customer Feedback and Information Extraction with Large Language Model [12.6020349733674]
  We propose a novel approach to extracting and analyzing transit-related information. Our method employs Large Language Models (LLM), specifically Llama 3, for a streamlined analysis. Our results demonstrate the potential of LLMs to transform social media data analysis in the public transit domain.
  arXiv  Detail & Related papers  (2024-10-19T07:08:40Z)
• LinkQ: An LLM-Assisted Visual Interface for Knowledge Graph Question-Answering [1.5238808518078564]
  LinkQ is a system that leverages a large language model (LLM) to facilitate knowledge graph (KG) query construction through natural language question-answering.<n>LLM interprets a user's question, then systematically converts it into a well-formed query.<n>LinkQ guards against the LLM hallucinating outputs by ensuring users' questions are only ever answered from ground truth KG data.
  arXiv  Detail & Related papers  (2024-06-07T15:28:31Z)
• Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models [54.55088169443828]
  Chain-of-Noting (CoN) is a novel approach aimed at improving the robustness of RALMs in facing noisy, irrelevant documents and in handling unknown scenarios. CoN achieves an average improvement of +7.9 in EM score given entirely noisy retrieved documents and +10.5 in rejection rates for real-time questions that fall outside the pre-training knowledge scope.
  arXiv  Detail & Related papers  (2023-11-15T18:54:53Z)
• RHO ($\rho$): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding [57.46495388734495]
  This paper presents RHO ($rho$) utilizing the representations of linked entities and relation predicates from a knowledge graph (KG) We propose (1) local knowledge grounding to combine textual embeddings with the corresponding KG embeddings; and (2) global knowledge grounding to equip RHO with multi-hop reasoning abilities via the attention mechanism.
  arXiv  Detail & Related papers  (2022-12-03T10:36:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.