EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A HYBRID LLM-BASED ARCHITECTURE FOR DOMAIN-SPECIFIC MATHEMATICAL MODEL CONSTRUCTION AND COMPUTATION

V R Bozhovskiy, H I Klym

Computer systems and network · 2026-06 · 8 (1) · 28-37

DOI: 10.23939/csn2026.01.028 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer systems and network, 2026-06. Verfasst von V R Bozhovskiy und 1 weiteren Autor:innen. Die Arbeit nennt 13 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models can interpret natural-language goals and formulate quantitative relationships; however, autonomous generation often leads to incomplete variable sets, hidden assumptions, and non-reproducible numerical results, especially under domain-specific constraints. This paper proposes a hybrid architecture that combines LLM-based construction of a domain-specific mathematical model with a deterministic computation layer. The system derives structured variables and executable expressions from a task description, validates inputs against domain rules, retrieves missing quantities from external knowledge sources when needed, and computes formulas in a controlled environment separated from probabilistic decoding. An end-to-end workflow is presented and experimentally evaluated on a diverse set of user tasks against a “LLM-only” baseline. We report task accuracy, input completeness, end-to-end pipeline latency, and the rate of partial outputs. The proposed approach improves accuracy from 72% to 97% and input completeness from 60% to 93%, while reducing the share of tasks with missing inputs from 40% to 4% and partial outputs from 28% to 3%; mean execution time is slightly higher than the baseline (4.2 s vs 2.3 s) due to validation and context retrieval overhead. The results indicate that separating semantic reasoning from deterministic execution improves the reliability of domain-specific mathematical modeling. Key words: computation, deterministic execution, domain-specific modeling, hybrid system, large language models, mathematical model, validation.

Zitieren

APA

Bozhovskiy, V. R., & Klym, H. I. (2026). A HYBRID LLM-BASED ARCHITECTURE FOR DOMAIN-SPECIFIC MATHEMATICAL MODEL CONSTRUCTION AND COMPUTATION. Computer systems and network, 8(1), 28-37. https://doi.org/10.23939/csn2026.01.028

Vancouver

Bozhovskiy VR, Klym HI. A HYBRID LLM-BASED ARCHITECTURE FOR DOMAIN-SPECIFIC MATHEMATICAL MODEL CONSTRUCTION AND COMPUTATION. Computer systems and network. 2026;8(1):28-37. doi:10.23939/csn2026.01.028

BibTeX
@article{Bozhovskiy2026,
  author = {Bozhovskiy, V R and Klym, H I},
  title = {A HYBRID LLM-BASED ARCHITECTURE FOR DOMAIN-SPECIFIC MATHEMATICAL MODEL CONSTRUCTION AND COMPUTATION},
  journal = {Computer systems and network},
  year = {2026},
  volume = {8},
  number = {1},
  pages = {28--37},
  doi = {10.23939/csn2026.01.028}
}
Kostenlos starten →