EUVIMEDEUVIMED entdecken
Crossref

Integrating Knowledge Graph with Retrieval-Augmented Generation for Vietnamese Legal Question Answering

Vuong T Pham, Minh Phan

DS Journal of Digital Science and Technology · 31.03.2025 · 5 (1) · 1-13

DOI: 10.59232/dst-v5i1p101 ↗

Kurz gefasst

Fachartikel in der Zeitschrift DS Journal of Digital Science and Technology, online erschienen am 31.03.2025. Verfasst von Vuong T Pham und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large Language Models (LLMs) are increasingly used for question answering, but legal applications require grounded answers with article-level citations and minimal unsupported statements. This paper presents a framework that integrates an ontology-driven Knowledge Graph (KG) with Retrieval-Augmented Generation (RAG) for Vietnamese legal question answering. The method builds a document-aware KG that preserves the hierarchical structure of statutes (Document → Chapter → Section → Article → Clause → Point) and encodes semantic and cross-reference relations. Graph-aware retrieval is combined with a hybrid ranking function that balances semantic similarity and graph-derived confidence, and the retrieved legal provisions are provided to an LLM using a constrained prompting template to generate answers with explicit citations. Experiments on three Vietnamese law domains (Electronic Transaction Law, Land Law, and Labor Law) report 85.7% answer accuracy, outperforming BM25 keyword search (62.3%) and a pure LLM baseline (71.5%), while improving citation quality. The framework is intended to increase traceability by grounding generation in retrieved statutory provisions.

Zitieren

APA

Pham, V. T., & Phan, M. (2025). Integrating Knowledge Graph with Retrieval-Augmented Generation for Vietnamese Legal Question Answering. DS Journal of Digital Science and Technology, 5(1), 1-13. https://doi.org/10.59232/dst-v5i1p101

Vancouver

Pham VT, Phan M. Integrating Knowledge Graph with Retrieval-Augmented Generation for Vietnamese Legal Question Answering. DS Journal of Digital Science and Technology. 2025;5(1):1-13. doi:10.59232/dst-v5i1p101

BibTeX
@article{Pham2025,
  author = {Pham, Vuong T and Phan, Minh},
  title = {Integrating Knowledge Graph with Retrieval-Augmented Generation for Vietnamese Legal Question Answering},
  journal = {DS Journal of Digital Science and Technology},
  year = {2025},
  volume = {5},
  number = {1},
  pages = {1--13},
  doi = {10.59232/dst-v5i1p101}
}
Kostenlos starten →