LLM-ACNC: Aerospace Requirement Texts Knowledge Graph Construction Utilizing Large Language Model
Open Access
Abstract
Traditional methods for requirement identification depend on the manual transformation of unstructured requirement texts into formal documents, a process that is both inefficient and prone to errors. Although requirement knowledge graphs offer structured representations, current named entity recognition and relation extraction techniques continue to face significant challenges in processing the specialized terminology and intricate sentence structures characteristic of the aerospace domain. To overcome these limitations, this study introduces a novel approach for constructing aerospace-specific requirement knowledge graphs using a large language model. The method first employs the GPT model for data augmentation, followed by BERTScore filtering to ensure data quality and consistency. An efficient continual learning based on token index encoding is then implemented, guiding the model to focus on key information and enhancing domain adaptability through fine-tuning of the Qwen2.5 (7B) model. Furthermore, a chain-of-thought reasoning framework is established for improved entity and relation recognition, coupled with a dynamic few-shot learning strategy that selects examples adaptively based on input characteristics. Experimental results validate the effectiveness of the proposed method, achieving F1 scores of 88.75% in NER and 89.48% in relation extraction tasks.Keywords
Funding Information
- China State Administration of Science, Technology and Industry for National Defense (D020101)
This publication has 28 references indexed in Scilit:
- Using Large Language Models for Natural Language Processing Tasks in Requirements Engineering: A Systematic Guideline2025
- SF-GPT: A training-free method to enhance capabilities for knowledge graph construction in LLMsNeurocomputing, 2024
- Challenges in applying large language models to requirements engineering tasksDesign Science, 2024
- A Unified Continual Learning Framework with General Parameter-Efficient Tuning2023
- An end-to-end deep learning system for requirements classification using recurrent neural networksInformation and Software Technology, 2022
- An approach to capturing and reusing tacit design knowledge using relational learning for knowledge graphsAdvanced Engineering Informatics, 2022
- Class-incremental Learning via Deep Model Consolidation2020
- Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence2018
- Learning without ForgettingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences, 2017