Skip to content
Open access

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

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.

Read PDF

Similar papers

Open access Sep 2026

Ontology driven cross language design smell detection through semantic reasoning

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...

Sabiyyah Sabir, Ghulam Rasool, Tariq Umer et al. · 0 citations

Enhancing Construction Requirements Documents Analytics through Integrating Ontology and Large Language Model

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. · 0 citations
Open access Oct 2026

A Model-Driven Metamodel for the Systematic Design of Configurable NLP Pipelines

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. · 0 citations
Conference Open access Sep 2026

Semantic-Driven Knowledge Assessment: Ontologies and Large Language Models for Automatic Test Generation

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. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.