Aug 2026· Journal of Computational Design and Engineering· Vol 13, pp. 29-51· 0 citations
TL;DR
This study proposes an LLM-based design document understanding approach for structurally organizing implicit design information embedded in unstructured design documents and demonstrates that the proposed approach can be directly applied to design automation tasks.
Abstract
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 an 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 (NLP) models and LLMs, achieving accuracy of 87.2% and 91.0%, respectively. Furthermore, a case study on automated design verification using real 3D CAD models demonstrates that the proposed approach can be directly applied to design automation tasks.
OD3 reverse-engineers source code from Java, C++, C#, Ruby, and Python into a unified semantic ontology and applies rule-based reasoning to identify violations of Object-Oriented (OO) design principles, supporting scalable, early-stage detection of design flaws across heterogeneous software systems while maintaining hi...
The results demonstrate the feasibility of the proposed framework for producing consistent sentence-level semantic extraction from quality-related construction requirement text and demonstrate how ontology-guided fine-tuning can provide explicit semantic grounding for LLM-based information extraction.
Lian-Nian Wang, Jeongbin Hwang, Kevin Han et al.· Journal of Management in Eng...· 0 citations
OmniExtract is an automatic data extraction tool with user-friendly configuration files which can adapt to various data extraction tasks and it can support a comprehensive data extraction including text and tables.
A metamodel is proposed in which the NLP pipeline itself is the modeling target, and fifteen metaclasses organized through explicit ownership semantics are defined, distinguishing pipeline-level, model-level, shared, and execution-generated components.
Kamal Walji, Allae Erraissi, Abdelali Zakrani et al.· International journal of adv...· 0 citations
This paper proposes a semantic-driven approach to automated knowledge assessment that integrates domain ontology modeling with the capabilities of large language models (LLMs) for generating test items with controlled difficulty. The core idea is to utilize formally structured knowledge, represented as an ontology, as...
A. Melnyk, Iurii Shcherbiak, Mariya Mudrak et al.· Automation, Control, and Inf...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.