A Study on the Interrelationship with SLM-based Knowledge Graph

Jeong-Sig Kim (김정식); Jinhong Kim (김진홍)

doi:10.29056/jsav.2025.09.11

A Study on the Interrelationship with SLM-based Knowledge Graph

Journal of Software Forensics
Abbr : JSF
2025, 21(3), pp.113~122
DOI : 10.29056/jsav.2025.09.11
Publisher : Korea Software Assessment and Valuation Society
Research Area : Engineering > Computer Science
Received : August 28, 2025
Accepted : September 20, 2025
Published : September 25, 2025

Jeong-Sig Kim ¹, Jinhong Kim ²

¹경기과학기술대학교
²배재대학교

Accredited

ABSTRACT

This paper explores the integration of Small Language Models (SLMs) with knowledge graphs (KGs) to enhance interoperability and knowledge representation. While Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding, their computational demands and lack of domain-specific focus present challenges. SLMs, with their smaller footprint and lower resource requirements, offer a promising alternative, particularly for creating and managing specialized knowledge graphs. We propose a novel framework that leverages SLMs to extract entities and relations from unstructured text, which are then used to construct and enrich a knowledge graph. This approach focuses on improving the interoperability between different knowledge sources by creating a unified, machine-readable representation.

KEYWORDS

small language models, knowledge graph, structured knowledge representations, framework

Journal Copyright Policy

No CCL information provided

Citation status

* References for papers published after 2025 are currently being built.

[other] / 2023 / The impact of large language models on scientific discovery: a preliminary study using gpt-4

[confproc] Akari Asai / 2023 / Self-rag: Learning to retrieve, generate, and critique through self-reflection / The Twelfth International Conference on Learning Representations

[other] Matthew Barker / 2025 / Faster, Cheaper, Better: Multi-Objective Hyperparameter Optimization for LLM and RAG Systems

[other] Yiqun Chen / 2025 / Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning

[other] Nurendra Choudhary / 2023 / Complex logical reasoning over knowledge graphs using large language models

[confproc] Wenqi Fan / 2024 / A survey on rag meeting llms: Towards retrievalaugmented large language models / Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining : 6491~6501 / https://dl.acm.org/doi/10.1145/3637528.3671470

[other] Shailja Gupta / 2024 / A comprehensive survey of retrieval-augmented generation (rag): Evolution, current landscape and future directions / arXiv preprint arXiv:2410.12837

[confproc] Xiaoxin He / 2024 / G-retriever: Retrieval-augmented generation for textual graph understanding and question answering / Advances in Neural Information Processing Systems 37 : 132876~132907

[other] Xanh Ho / 2020 / Constructing a multi-hop qa dataset for comprehensive evaluation of reasoning steps

[journal] Lei Huang / 2025 / A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions / ACM Transactions on Information Systems 43(2) : 1~55

[other] Kush Juvekar / 2024 / Introducing a new hyper-parameter for RAG: Context Window Utilization

[journal] Ernests Lavrinovics / 2025 / Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspective / Journal of Web Semantics 85 : 100844~

[confproc] R. Hu / 2023 / Evaluation of Hallucination and Robustness for Large Language Models / 2023 IEEE 23rd International Conference on Software Quality, Reliability, and Security Companion(QRS-C) : 374~382

[confproc] Patrick Lewis / 2020 / Retrieval-augmented generation for knowledge-intensivenlp tasks / Advances in neural information processing systems 33 : 9459~9474 / https://dl.acm.org/doi/abs/10.5555/3495724.3496517

KJCKorea
Journal Central

Journal of Software Forensics 2025 KCI Impact Factor : 0.3

A Study on the Interrelationship with SLM-based Knowledge Graph

ABSTRACT

KEYWORDS

Journal Copyright Policy

Citation status

* References for papers published after 2025 are currently being built.

Journal of Software Forensics 2025 KCI Impact Factor : 0.3

A Study on the Interrelationship with SLM-based Knowledge Graph

ABSTRACT

KEYWORDS

Journal Copyright Policy

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (0)

REFERENCES (14) * References for papers published after 2025 are currently being built.

Search PDF

Citation

* References for papers published after 2025 are currently being built.