Hierarchical knowledge graph-based QA systems with retrieval-augmented generation
Enterprise Information Systems · 02.01.2026 · 20 (1)
DOI: 10.1080/17517575.2025.2580477 ↗Kurz gefasst
Fachartikel in der Zeitschrift Enterprise Information Systems, online erschienen am 19.11.2025. Verfasst von Wan-Chi Yang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 41 Literaturangaben.
Abstract (Originalsprache)
Hierarchical knowledge graphs (KGs) are vital to question-answering (QA) systems for complex queries, integrating structured and unstructured knowledge. This study introduces a QA system combining a hierarchical KG, graph convolutional networks (GCNs), and retrieval-augmented generation (RAG) to enhance reasoning, retrieval, and response generation. The KG organises information into title, subtitle, and content layers for structured, efficient retrieval; GCNs aggregate local and global relations across layers; RAG incorporates external sources (e.g., Wikipedia) for contextually accurate answers. On standard benchmarks, the system outperformed strong baselines in precision, recall, and F1-score, offering an effective solution for complex queries and advancing QA design.
Zitieren
APA
Yang, W., Li, X., Chang, C., & Roy, D. S. (2026). Hierarchical knowledge graph-based QA systems with retrieval-augmented generation. Enterprise Information Systems, 20(1). https://doi.org/10.1080/17517575.2025.2580477
Vancouver
Yang W, Li X, Chang C, Roy DS. Hierarchical knowledge graph-based QA systems with retrieval-augmented generation. Enterprise Information Systems. 2026;20(1). doi:10.1080/17517575.2025.2580477
BibTeX
@article{Yang2026,
author = {Yang, Wan-Chi and Li, Xuan and Chang, Chih-Yung and Roy, Diptendu Sinha},
title = {Hierarchical knowledge graph-based QA systems with retrieval-augmented generation},
journal = {Enterprise Information Systems},
year = {2026},
volume = {20},
number = {1},
doi = {10.1080/17517575.2025.2580477}
}
EUVIMED