LLMs-based weighting for MCDM: case study in logistics performance index

Nurcan Deniz

Abstract


Purpose: The aim of this paper is to conduct an experimental study to determine whether LLMs-based weighting is suitable for MCDM or not. In addition, to analyze the prompt design effect is a purpose of this study.

Design/methodology/approach: In this study experiments carried out based on prompts to determine the weights of six criteria in Logistics Performance Index.  

Findings/results: The findings revealed that; prompt design is the most critical part to integrate LLMs in MCDM context. Results show that answers of the ChatGPT differs with different prompt types and examples.

Practical implications: The findings of this study is beneficial for the researchers in MCDM area who wants to integrate LLMs in the field. The study will help not only the professionals in the logistics sector but also the beginners.

Originality/value: There are some recent studies used LLMs in MCDM context. To the best of our knowledge, it is the first study used in logistics performance evaluation.

 

Received on: 02 June 2025

Accepted on: 06 January 2026

Published on: 07 April 2026


Keywords


LLMs, prompt, ChatGPT, LLMs-based weighting, MCDM, logistics, Logistics Performance Index, generative artificial intelligence

Full Text:

PDF

References


Bozkurt, A. (2024). Tell Me Your Prompts and I Will Make Them True: The Alchemy of Prompt Engineering and Generative AI. Open praxis, 16(2), pp.111–118. doi:https://doi.org/10.55982/openpraxis.16.2.661.

Çalık, A., Erdebilli, B. and Özdemir, Y.S. (2022). Novel Integrated Hybrid Multi-Criteria Decision-Making Approach for Logistics Performance Index. Transportation Research Record: Journal of the Transportation Research Board, p.036119812211133. doi:https://doi.org/10.1177/03611981221113314.

Chejarla, K.C., Vaidya, O.S. and Kumar, S. (2021). MCDM applications in logistics performance evaluation: A literature review. Journal of Multi-Criteria Decision Analysis. doi:https://doi.org/10.1002/mcda.1774.

Çıray, D., Özdemir, Ü. and Mete, S. (2024). An Evaluation of the logistics Performance Index Using the ENTROPY-based ORESTE Method. Journal of Transportation and Logistics, 0(0). doi:https://doi.org/10.26650/jtl.2024.1437070.

Dehghanimohammadabadi, M. and Kabadayı, N. (2024). The Ai-Driven Decision-Making (Aidm) Framework: Integrating Ahp and Chatgpt-4 for Supplier Selection. [online] doi:https://doi.org/10.2139/ssrn.4997750.

Frederico, G.F. (2023). ChatGPT in Supply Chains: Initial Evidence of Applications and Potential Research Agenda. Logistics, 7(2), p.26. doi:https://doi.org/10.3390/logistics7020026.

Gürler, H.E., Özçalıcı, M. and Pamucar, D. (2023). Determining criteria weights with genetic algorithms for multi-criteria decision making methods: The case of logistics performance index rankings of European Union countries. Socio-Economic Planning Sciences, 91, pp.101758–101758. doi:https://doi.org/10.1016/j.seps.2023.101758.

Hadžikadunić, A., Stević, Ž., Badi, I. and Roso, V. (2023). Evaluating the Logistics Performance Index of European Union Countries: An Integrated Multi-Criteria Decision-Making Approach Utilizing the Bonferroni Operator. International Journal of Knowledge and Innovation Studies, 1(1), pp.44–59. doi:https://doi.org/10.56578/ijkis010104.

Işık, Ö., Aydın, Y. and Koşarolu, Ş. (2020). The assessment of the logistics performance index of cee countries with the new combination of sv and mabac methods. LogForum, 16(4), pp.549–559. doi:https://doi.org/10.17270/j.log.2020.504.

Kara, K., Bentyn, Z. and Yalçın, G.C. (2022). Determining the logistics market performance of developing countries by Entropy and MABAC methods. Logforum, 18(4), pp.421–434. doi:https://doi.org/10.17270/j.log.2022.752.

Kmiecik, M. (2023). ChatGPT in third-party logistics – The game-changer or a step into the unknown? Journal of Open Innovation: Technology, Market, and Complexity, [online] 9(4), p.100174. doi:https://doi.org/10.1016/j.joitmc.2023.100174.

Lu, X., Li, J., Takeuchi, K. and Kashima, H. (2024). AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended Responses. arXiv (Cornell University). doi:https://doi.org/10.48550/arxiv.2410.01246.

Mešić, A., Miškić, S., Stević, Ž. and Mastilo, Z. (2022). Hybrid MCDM Solutions for Evaluation of the Logistics Performance Index of the Western Balkan Countries. ECONOMICS, 10(1), pp.13–34. doi:https://doi.org/10.2478/eoik-2022-0004.

Özekenci, E.K. (2025). EVALUATION OF THE LOGISTICS PERFORMANCE INDEX OF OECD COUNTRIES BASED ON HYBRID MCDM METHODS. Marmara Üniversitesi İktisadi ve İdari Bilimler Dergisi, 47(1), pp.47–76. doi:https://doi.org/10.14780/muiibd.1469898.

Park, H., Oh, H., Gao, F. and Kwon, O. (2025). Enhancing Analytic Hierarchy Process Modelling Under Uncertainty With Fine‐Tuning LLM. Expert Systems, 42(6). doi:https://doi.org/10.1111/exsy.70051.

Ray, P.P. (2023). ChatGPT: a Comprehensive Review on background, applications, Key challenges, bias, ethics, Limitations and Future Scope. Internet of Things and Cyber-Physical Systems, [online] 3(1), pp.121–154. doi:https://doi.org/10.1016/j.iotcps.2023.04.003.

Rezaei, J. (2015). Best-worst multi-criteria decision-making method. Omega, 53, pp.49–57. doi:https://doi.org/10.1016/j.omega.2014.11.009.

Svoboda, I. and Lande, D. (2024). Enhancing Multi-Criteria Decision Analysis with AI: Integrating Analytic Hierarchy Process and GPT-4 for Automated Decision Support. [online] arXiv.org. Available at: https://arxiv.org/abs/2402.07404.

The World Bank (2023). Connecting to Compete 2023 Trade Logistics in the Global Economy The Logistics Performance Index and Its Indicators. [online] Washington. Available at: https://lpi.worldbank.org/sites/default/files/2023-04/LPI_2023_report_with_layout.pdf.

Ulutaş, A. and Karaköy, Ç. (2019). An analysis of the logistics performance index of EU countries with an integrated MCDM model. Economics and Business Review, 5(4), pp.49–69. doi:https://doi.org/10.18559/ebr.2019.4.3.

Wamba, S.F., Guthrie, C., Queiroz, M.M. and Minner, S. (2023). ChatGPT and generative artificial intelligence: an exploratory study of key benefits and challenges in operations and supply chain management. International Journal of Production Research, 62(16), pp.1–21. doi:https://doi.org/10.1080/00207543.2023.2294116.

Wang, H., Zhang, F. and Mu, C. (2025). One for All: A General Framework of LLMs-based Multi-Criteria Decision Making on Human Expert Level. [online] arXiv.org. Available at: https://arxiv.org/abs/2502.15778.

Wang, X. and Wu, X. (2024). Can ChatGPT Serve as a Multi-Criteria Decision Maker? A Novel Approach to Supplier Evaluation. ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.10281–10285. doi:https://doi.org/10.1109/icassp48485.2024.10447204.

Yildirim, B.F. and Adiguzel Mercangoz, B. (2019). Evaluating the logistics performance of OECD countries by using fuzzy AHP and ARAS-G. Eurasian Economic Review, 10(1), pp.27–45. doi:https://doi.org/10.1007/s40822-019-00131-3.

Yılmaz, B. (2025). Determining The Digitalization Levels of Leading Countries in Logistics Performance Index: An Application with CRITIC-TOPSIS Approach. Verimlilik Dergisi, 59(2), pp.431–450. doi:https://doi.org/10.51551/verimlilik.1541480.




DOI: https://dx.doi.org/10.21622/IBL.2026.06.1.1408

Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Nurcan Deniz

International Business Logistics

E-ISSN: 2735-5969

P-ISSN: 2735-5950

 

Published by:

Academy Publishing Center (APC)

Arab Academy for Science, Technology and Maritime Transport (AASTMT)

Alexandria, Egypt

ibl@aast.edu