EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

LLM-based design document understanding for semantic knowledge extraction and design verification

Junho Kim, Sangwook Park, Seungeun Lim, Hyeonji Lee, Duhwan Mun

Journal of Computational Design and Engineering · 29.08.2026 · 13 (9) · 29-51

DOI: 10.1093/jcde/qwag074 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computational Design and Engineering, online erschienen am 11.08.2026. Verfasst von Junho Kim und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Basic Science Research Program, Ministry of Science and ICT, South Korea, Ministry of Trade, Industry and Energy.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Design documents contain essential design knowledge such as designers’ intent, decision-making criteria, and constraints, and are widely used to support accurate and consistent product development. Most design documents are extensive and composed of unstructured natural language-based text, which makes it difficult for humans to manually read and retrieve relevant information efficiently. To address this challenge, this study proposes a Large Language Model (LLM)-based design document understanding approach for structurally organizing implicit design information embedded in unstructured design documents. A sentence-level semantic classification framework is introduced to categorize design sentences according to quantitative and functional characteristics. In addition, contextual information is leveraged to identify the design object described by each sentence automatically. Design semantics classification and design object identification experiments were conducted by fine-tuning various Natural Language Processing models and LLMs, achieving accuracies of 87.2% and 91.0%, respectively. Furthermore, a case study on automated design verification using real 3D Computer Aided Design (CAD) models demonstrates that the proposed approach can be directly applied to design automation tasks.

Förderung

  • Basic Science Research Program
  • Ministry of Science and ICT, South Korea
  • Ministry of Trade, Industry and Energy

Zitieren

APA

Kim, J., Park, S., Lim, S., Lee, H., & Mun, D. (2026). LLM-based design document understanding for semantic knowledge extraction and design verification. Journal of Computational Design and Engineering, 13(9), 29-51. https://doi.org/10.1093/jcde/qwag074

Vancouver

Kim J, Park S, Lim S, Lee H, Mun D. LLM-based design document understanding for semantic knowledge extraction and design verification. Journal of Computational Design and Engineering. 2026;13(9):29-51. doi:10.1093/jcde/qwag074

BibTeX
@article{Kim2026,
  author = {Kim, Junho and Park, Sangwook and Lim, Seungeun and Lee, Hyeonji and Mun, Duhwan},
  title = {LLM-based design document understanding for semantic knowledge extraction and design verification},
  journal = {Journal of Computational Design and Engineering},
  year = {2026},
  volume = {13},
  number = {9},
  pages = {29--51},
  doi = {10.1093/jcde/qwag074}
}
Kostenlos starten →