EUVIMEDEUVIMED entdecken
Crossref

Auditable LLM-assisted decision support for sustainable infrastructure planning

Ali Elkliny, Tareq Khaled Abdulwasea, Abubakar Sadiq Ibrahim, Xiaopeng Deng, Mohamed Gaber

Proceedings of the Institution of Civil Engineers - Engineering Sustainability · 14.09.2026 · 1-43

DOI: 10.1680/jensu.26.00094 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the Institution of Civil Engineers - Engineering Sustainability, online erschienen am 14.09.2026. Verfasst von Ali Elkliny und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: National Science and Technology Major Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sustainable infrastructure decisions frequently rely on expert knowledge expressed in narrative form, creating a gap between qualitative judgement and the structured numerical inputs required by multi-criteria decision making methods. This study proposes an auditable large language model (LLM)-enabled decision-support workflow integrating the ordinal priority approach (OPA), a genetic algorithm (GA), and the technique for order preference by similarity to ideal solution (TOPSIS). Five construction-management experts provided memoranda on duration, cost, and environmental-impact trade-offs for a road project in Egypt. Five ChatGPT variants GPT-4.1, GPT-4.1-mini, GPT-4.1-nano, GPT-4o, and GPT-4o-mini were evaluated using identical prompts, temperature-0 decoding, no external retrieval, numerical validation, and expert review of rationale fidelity and weight consistency. OPA identified GPT-4o as the most aligned model, with a priority of 0.256. The selected LLM generated criterion weights for TOPSIS, while the GA produced 500 dataset-feasible alternatives. Using weights of 0.34, 0.33, and 0.33 for duration, cost, and environmental impact, respectively, TOPSIS used the LLM-derived criterion weights to distinguish among 500 feasible alternatives across the three decision criteria. The workflow provides a transparent and reviewable pathway from narrative expert judgement to quantitative infrastructure decision support, strengthening the auditability of LLM-enabled multi-criteria decision processes.

Förderung

  • National Science and Technology Major Project

Zitieren

APA

Elkliny, A., Abdulwasea, T. K., Ibrahim, A. S., Deng, X., & Gaber, M. (2026). Auditable LLM-assisted decision support for sustainable infrastructure planning. Proceedings of the Institution of Civil Engineers - Engineering Sustainability, 1-43. https://doi.org/10.1680/jensu.26.00094

Vancouver

Elkliny A, Abdulwasea TK, Ibrahim AS, Deng X, Gaber M. Auditable LLM-assisted decision support for sustainable infrastructure planning. Proceedings of the Institution of Civil Engineers - Engineering Sustainability. 2026:1-43. doi:10.1680/jensu.26.00094

BibTeX
@article{Elkliny2026,
  author = {Elkliny, Ali and Abdulwasea, Tareq Khaled and Ibrahim, Abubakar Sadiq and Deng, Xiaopeng and Gaber, Mohamed},
  title = {Auditable LLM-assisted decision support for sustainable infrastructure planning},
  journal = {Proceedings of the Institution of Civil Engineers - Engineering Sustainability},
  year = {2026},
  pages = {1--43},
  doi = {10.1680/jensu.26.00094}
}
Kostenlos starten →