Tradespace Analysis Using Generative Pre-Trained Transformer: A Comparative Study With Humans
Journal of Computing and Information Science in Engineering · 01.12.2026 · 26 (12)
DOI: 10.1115/1.4072639 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computing and Information Science in Engineering, online erschienen am 21.09.2026. Verfasst von Mozhdeh Rahmanpour und 4 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
With large language models (LLMs) becoming ever more popular and their usage expanding into various domains, this study explores how effective an LLM like generative pre-trained transformer (GPT)-4 would be in analyzing requirement specification documents and using relevant information from those to create a tradespace matrix. This study compares GPT-4’s performance with that of 30 human participants from diverse backgrounds, categorized into three groups: engineering, non-technical, and CS/AI. Each participant and the LLM completed a survey based on materials provided for evaluating a complex system design and populating a tradespace matrix. The analysis of these responses included within-group heatmaps, across-group comparisons, and human-versus-GPT-4 heatmap evaluations. The results show that the CS/AI group had the most closely aligned responses with GPT-4. This study demonstrates how LLMs can augment tradespace exploration and serve as an alternative in cases where employing a team of human experts from multiple backgrounds is not feasible.
Zitieren
APA
Rahmanpour, M., Kumar, A. A., Joy, D., Baby, M., & Morkos, B. (2026). Tradespace Analysis Using Generative Pre-Trained Transformer: A Comparative Study With Humans. Journal of Computing and Information Science in Engineering, 26(12). https://doi.org/10.1115/1.4072639
Vancouver
Rahmanpour M, Kumar AA, Joy D, Baby M, Morkos B. Tradespace Analysis Using Generative Pre-Trained Transformer: A Comparative Study With Humans. Journal of Computing and Information Science in Engineering. 2026;26(12). doi:10.1115/1.4072639
BibTeX
@article{Rahmanpour2026,
author = {Rahmanpour, Mozhdeh and Kumar, Aathira Anil and Joy, David and Baby, Mathew and Morkos, Beshoy},
title = {Tradespace Analysis Using Generative Pre-Trained Transformer: A Comparative Study With Humans},
journal = {Journal of Computing and Information Science in Engineering},
year = {2026},
volume = {26},
number = {12},
doi = {10.1115/1.4072639}
}
EUVIMED