PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 22, 2026Buildings0 citationsOpen Access

Claim Knowledge Graph Construction and GraphRAG-Based Question-Answering System

View Full Paper
XWXinxue WangJFJun Fang

Key Points

  • The aim is to develop a domain-specific ontology and knowledge graph for construction engineering claims to improve claim management efficiency.
  • Constructed an ontology for construction engineering claims through a five-step process.
  • Built a knowledge graph stored in Neo4j.
  • Evaluated a knowledge graph-enhanced LLM question-answering system using multiple performance metrics.
  • Compared the performance of the new system against a base LLM and Vector RAG approaches.
  • The knowledge graph-enhanced LLM system outperformed the base LLM and Vector RAG in question-answering tasks.
  • Evaluation metrics including BLEU-4, BERT-Cosine similarity, ROUGE-1, and ROUGE-L showed significant improvements.
  • The ontology facilitated effective knowledge sharing and reuse for construction claims.

Abstract

Traditional claim management relies heavily on manual analysis and expert judgment, resulting in inefficiencies, information omissions, and heightened risks of disputes. To address these challenges, this paper constructs a domain-specific ontology for construction engineering claims through a five-step process, organizing the relevant knowledge into five unified core classes. Based on this ontology, a knowledge graph is built and stored in Neo4j. The resulting knowledge graph-enhanced LLM question-answering system, evaluated using BLEU-4, BERT-Cosine similarity, ROUGE-1, and ROUGE-L metrics, demonstrates superior performance compared to both the base LLM and Vector RAG approaches. The results indicate that the proposed ontology effectively serves the purpose of knowledge sharing and reuse while providing practical support for construction claim management.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Wang et al. (2026) studied this question.

synapsesocial.com/papers/699a9d8e482488d673cd3890https://doi.org/10.3390/buildings16040845
Ask AI
Helpful
Bookmark
Share
View Full Paper