Comparative Analysis of LLM-based Graph Represenation Construction for Domain-specific Documents
Electronics and Control Systems · 19.04.2026 · 2 (88) · 86-92
DOI: 10.18372/1990-5548.88.20970 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics and Control Systems, online erschienen am 19.04.2026. Verfasst von Illia Savenko. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Recent advances in large language models have substantially improved natural language understanding and enabled their application across a wide range of domains. However, highly specialized fields such as law and medicine remain challenging because their documents often contain complex structures, domain-specific terminology, and dense logical dependencies. In such settings, large language models may produce errors when important structural information is not explicitly preserved in the document representation. To address this limitation, we propose a novel approach for document decomposition into graph-based representations that better capture the structural and semantic relationships within complex texts. We develop a method for processing raw legal documents from the Ukrainian domain using an LLM-based decomposition pipeline, transforming them into structured graph representations that can reinforce contextual retrieval and support retrieval-augmented generation. The proposed method improves document understanding by preserving key contextual dependencies and enhancing the representation of legal knowledge in downstream tasks.
Zitieren
APA
Savenko, I. (2026). Comparative Analysis of LLM-based Graph Represenation Construction for Domain-specific Documents. Electronics and Control Systems, 2(88), 86-92. https://doi.org/10.18372/1990-5548.88.20970
Vancouver
Savenko I. Comparative Analysis of LLM-based Graph Represenation Construction for Domain-specific Documents. Electronics and Control Systems. 2026;2(88):86-92. doi:10.18372/1990-5548.88.20970
BibTeX
@article{Savenko2026,
author = {Savenko, Illia},
title = {Comparative Analysis of LLM-based Graph Represenation Construction for Domain-specific Documents},
journal = {Electronics and Control Systems},
year = {2026},
volume = {2},
number = {88},
pages = {86--92},
doi = {10.18372/1990-5548.88.20970}
}
EUVIMED