Applied Research Advances

Vol. 2 No. 1 (2026): Applied Research Advances
Articles

Large Language Models in Multi Criteria Decision Making: A Systematic Review, Taxonomy, and Future Research Agenda

Full text (pdf)
  • Sushil Kumar Sahoo,
  • Bibhuti Bhusan Choudhury,
  • Prasant Ranjan Dhal,
  • Supriya Sahu,
  • Sudhakar Majhi,
  • Ipsita Dhar
Sushil Kumar Sahoo
Department of Mechanical Engineering, Indira Gandhi Institute of Technology, Sarang, Odisha, India
Bibhuti Bhusan Choudhury
Department of Mechanical Engineering, Indira Gandhi Institute of Technology, Sarang, Odisha, India
Prasant Ranjan Dhal
Department of Mechanical Engineering, Indira Gandhi Institute of Technology, Sarang, Odisha, India
Supriya Sahu
Department of Mechanical Engineering, Indira Gandhi Institute of Technology, Sarang, Odisha, India
Sudhakar Majhi
Department of Mechanical Engineering, Indira Gandhi Institute of Technology, Sarang, Odisha, India
Ipsita Dhar
Department of Mechanical Engineering, Indira Gandhi Institute of Technology, Sarang, Odisha, India

Published 2026-05-09

Keywords

  • Multi Criteria Decision Making,
  • Large Language Models,
  • Artificial Intelligence,
  • Decision Support Systems,
  • Bibliometric Analysis,
  • Literature Review ,
  • MCDM
    • ...More
    Less

Copyright (c) 2026 Sushil Kumar Sahoo, Bibhuti Bhusan Choudhury, Prasant Ranjan Dhal, Supriya Sahu, Sudhakar Majhi, Ipsita Dhar (Author)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Sahoo, S. K., Choudhury, B. B., Dhal, P. R., Sahu, S., Majhi, S., & Dhar, I. (2026). Large Language Models in Multi Criteria Decision Making: A Systematic Review, Taxonomy, and Future Research Agenda. Applied Research Advances, 2(1), 116-136. https://doi.org/10.65069/ara21202614
Crossref
Scopus
Google Scholar
Europe PMC

Abstract

This study is a systematic review, bibliometric analysis and taxonomy building of Large Language Models (LLM) and Multi-Criteria Decision-Making (MCDM) integration. A total of 63 publications from the Scopus database were analysed using PRISMA guidelines and VOSviewer tools. The findings show this field is highly nascent, with a rapid rise since 2025. Bibliometric analysis shows that this field is widely practiced globally, with 37 countries involved and China and India contributing most publications. This study introduces a new classification system based on the roles of LLM, the integration stages and the application areas. Comparative studies show LLM-enhanced MCDM improves automation, scalability, and unstructured data processing, but remains prone to biases, lack of interpretability and sensitivity to prompts. The research concludes with gaps and opportunities to advance this field towards robust, explainable and hybrid intelligent decision-making systems.

Full text (pdf)

Downloads

Download data is not yet available.

References

  1. Komatina, N., & Marinković, D. (2026). An objective multi-attribute decision-making framework for identifying critical phases in automotive component manufacturing. Journal of Engineering Management and Systems Engineering. https://doi.org/10.56578/jemse050101
  2. Yalçın, G. C. (2025). Development of a fuzzy-based decision support system for sustainable tractor selection in green ports. Facta Universitatis, Series: Mechanical Engineering, 23(3), 579-604. https://doi.org/10.22190/FUME250610029Y
  3. Badi, I., Bouraima, M. B., & Kiptum, C. K. (2026). Evaluating the Barriers to Logistics Outsourcing through a Fuzzy Multi-Criteria Decision-Making Model. Spectrum of Mechanical Engineering and Operational Research, 3(1), 65-78. https://doi.org/10.31181/smeor31202653
  4. Kristiani, E., Verma, V. K., & Yang, C. T. (2026). Deploying LLM Transformer on Edge Computing Devices: A Survey of Strategies, Challenges, and Future Directions. AI, 7(1), 15. https://doi.org/10.3390/ai7010015
  5. Chen, B., Zhang, Z., Langrené, N., & Zhu, S. (2025). Unleashing the potential of prompt engineering for large language models. Patterns, 6(6). https://doi.org/10.1016/j.patter.2025.101260
  6. Sahoo, S. K., & Choudhury, B. B. (2021). A fuzzy AHP approach to evaluate the strategic design criteria of a smart robotic powered wheelchair prototype. In Intelligent Systems: Proceedings of ICMIB 2020 (pp. 451-464). Singapore: Springer Singapore. https://doi.org/10.1007/978-981-33-6081-5_40
  7. Sahoo, S. K., Choudhury, B. B., & Dhal, P. R. (2027). A Comprehensive Review of Fuzzy Multiple Criteria Decision-Making (MCDM) Methods: Advancements, Applications, and Future Directions. Spectrum of Decision Making and Applications. https://doi.org/10.31181/sdmap41202764
  8. Song, C., & Syed Zakaria, S. A. (2025). Comprehensive Risk Assessment for Engineering, Procurement, and Construction (EPC)-Based Prefabricated Buildings Using Analytic Network Process (ANP)–Gray Clustering Analysis. Buildings, 15(24), 4516. https://doi.org/10.3390/buildings15244516
  9. Sahoo, S. K., Choudhury, B. B., & Dhal, P. R. (2024). A bibliometric analysis of material selection using MCDM methods: trends and insights. Spectrum of mechanical engineering and operational research, 1(1), 189-205. https://doi.org/10.31181/smeor11202417
  10. Unanoglu, M. (2025). Evaluating Innovation, Quality of Life and Sustainability in OECD Countries: A Vikor Approach. Maliye ve Finans Yazıları, (Özel Sayı 3), 279-298. https://doi.org/10.33203/mfy.1830836
  11. Ervural, B. C. (2026). Evaluating the sustainable development performance of G20 economies using an integrated decision-making framework. Journal of Engineering Management and Systems Engineering, 5(1), 63-84. https://doi.org/10.56578/jemse050105
  12. Kumar, R. (2025). A comprehensive review of MCDM methods, applications, and emerging trends. Decision Making Advances, 3(1), 185-199. https://doi.org/10.31181/dma31202569
  13. García-Gutiérrez, E., Aguilar-Torres, D., Jiménez-Ramírez, O., Carvajal-Quiroz, E., & Vázquez-Medina, R. (2026). Ultra-Low-Power Energy Harvesters for IoT-Based Germination Systems: A Decision Framework Using Multi-Criteria Analysis. Technologies, 14(2), 82. https://doi.org/10.3390/technologies14020082
  14. Chakraborty, S., Raut, R. D., Rofin, T. M., & Chakraborty, S. (2025). A narrative literature review on optimization of manufacturing processes using weighted aggregated sum product assessment (WASPAS) method. OPSEARCH, 62(3), 1616-1640. https://doi.org/10.1007/s12597-024-00858-x
  15. Hou, H. (2025). Utility Theory Application in Decision-Making Behavior for Energy Use and Management: A Systematic Review. Energies, 18(8), 2125. https://doi.org/10.3390/en18082125
  16. Sun, G., Kroesen, M., & Rezaei, J. (2026). Anchoring Bias in the Tradeoff Procedure Within Multi‐Attribute Value Theory. Journal of Behavioral Decision Making, 39(2), e70069. https://doi.org/10.1002/bdm.70069
  17. Albahri, O. S., Alsalem, M. A., Albahri, A. S., A. Mahmoud, M., Alzubaidi, L., Alamoodi, A. H., & Mohamad Sharaf, I. (2025). An Improved Best‐Worst Method Integrated With Combined Compromise Solution for Evaluating Large Language Models. International Journal of Intelligent Systems, 2025(1), 2376097. https://doi.org/10.1155/int/2376097
  18. Agarwal, S., Tyagi, M., Garg, R. K., & Chopra, A. (2025). Optimizing sustainable supply of essential materials in a circular economy: a CoCoSo-SWARA based approach. Journal of Remanufacturing, 15(1), 1-23. https://doi.org/10.1007/s13243-024-00141-8
  19. He, H., Zhou, Z., Sun, Y., & Li, Q. (2025). Fire risk assessment and simulation of multi-functional teaching buildings: A combined application of DEMATEL and PyroSim. Journal of Engineering Management and Systems Engineering, 4(1), 1-20. https://doi.org/10.56578/jemse040101
  20. Chen, X., & Ji, W. (2025). DSM-CoCoSo Technique for Intuitionistic Fuzzy Multiple-Attribute Group Decision-Making and Applications to Construction Engineering Quality Management Evaluation. International Journal of Fuzzy Systems, 1-15. https://doi.org/10.1007/s40815-025-02133-7
  21. Sahoo, S. K., & Goswami, S. S. (2023). A comprehensive review of multiple criteria decision-making (MCDM) methods: advancements, applications, and future directions. Decision making advances, 1(1), 25-48. https://doi.org/10.31181/dma1120237
  22. Wang, C. N., & Thi, D. O. T. (2026). Lean-oriented facility layout optimization using an AHP-COPRAS Framework: a case study of a Vietnamese Garment. The International Journal of Advanced Manufacturing Technology, 1-12. https://doi.org/10.1007/s00170-026-17821-3
  23. Mehdiabadi, A., Sadeghi, A., Yazdi, A. K., & Tan, Y. (2025). Sustainability service chain capabilities in the oil and gas industry: A fuzzy hybrid approach SWARA-MABAC. Spectrum of operational research, 2(1), 114-134. https://doi.org/10.31181/sor21202512
  24. Imran, R., & Ullah, K. (2025). Circular intuitionistic fuzzy EDAS approach: A new paradigm for decision-making in the automotive industry sector. Spectrum of Engineering and Management Sciences, 3(1), 76-92. https://doi.org/10.31181/sems31202537i
  25. Bhowmik, C., Zindani, D., Chatterjee, P., Marinkovic, D., & Šliogerienė, J. (2025). Evaluation of green energy sources: an extended fuzzy-todim approach based on schweizer-sklar and power averaging operators. Facta Universitatis, Series: Mechanical Engineering, 23(3), 627-648. https://doi.org/10.22190/FUME240711042B
  26. Das, S., Ghadai, R. K., Sapkota, G., Guha, S., Barmavatu, P., & Kumar, K. R. (2025). Optimization of CNC turning parameters of copper–nickel (Cu–Ni) alloy using VIKOR, MOORA and GRA techniques. International Journal on Interactive Design and Manufacturing (IJIDeM), 19(1), 291-300. https://doi.org/10.1007/s12008-023-01698-7
  27. Hu, A., & Xie, N. (2025). Construction and application of a novel grey relational analysis model considering factor coupling relationship. Grey Systems: Theory and Application, 15(1), 1-20. https://doi.org/10.1108/GS-04-2024-0046
  28. Božanić, D., Puška, A., Tešić, D., Štilić, A., Ullah, K., Muhsen, Y. R., & Hezam, I. M. (2025). FUZZY AHP-FUZZY MABAC MODEL FOR RANKING A COMBINED CONSTRUCTION MACHINE-BACKHOE LOADER. Facta Universitatis, Series: Mechanical Engineering, 23(3), 605-625. https://doi.org/10.22190/FUME250801030B
  29. Biswas, A., Gazi, K. H., Sankar, P. M., & Ghosh, A. (2025). A decision-making framework for sustainable highway restaurant site selection: AHP-TOPSIS approach based on the fuzzy numbers. Spectrum of operational research, 2(1), 1-26. https://doi.org/10.31181/sor2120256
  30. Mishra, A. R., Rani, P., Pamucar, D., Alshamrani, A. M., & Alrasheedi, A. F. (2025). Intuitionistic fuzzy MACONT method for logistics 4.0 based circular economy interested regions assessment in the agri-food sector. Facta Universitatis, Series: Mechanical Engineering, 23(3), 407-432. https://doi.org/10.22190/FUME241001052M
  31. Gül, A. Y., Cakmak, E., & Karakas, A. E. (2025). Drone selection for forest surveillance and fire detection using interval valued neutrosophic edas method. Facta Universitatis, Series: Mechanical Engineering, 23(3), 433-458. https://doi.org/10.22190/FUME231028008G
  32. Gul, R. (2025). An extension of VIKOR approach for MCDM using bipolar fuzzy preference δ-covering based bipolar fuzzy rough set model. Spectrum of Operational Research, 2(1), 72-91. https://doi.org/10.31181/sor21202511
  33. Žižović, M., & Albijanić, M. (2025). An Implementation of the Entropy Method for Determining Weighing Coefficients in a Multicriteria Optimization of Public Procurements. Spectrum of Engineering and Management Sciences, 3(1), 28-44. https://doi.org/10.31181/sems31202528z
  34. Dhal, P. R., Choudhury, B. B., & Sahoo, S. K. (2025). Evaluation of motorized wheelchairs using an integrated ARAS-TOPSIS and CRITIC approach. AiBi Revista de Investigación, Administración e Ingeniería, 13(2), 1-14. https://doi.org/10.15649/2346030X.4013
  35. Arif, R., Mondal, S., & Mandal, N. P. (2025). WASPAS based Taguchi approach to reduce the energy consumption of a typical office building. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 239(14), 5709-5725. https://doi.org/10.1177/09544062251327546
  36. Yüksel, S., Eti, S., Dinçer, H., Köklü, K., & Acar, M. (2026). Artificial Intelligence-Enhanced Policy Evaluation of Short-and Long-Term Hydrogen Strategies in Emerging and Advanced Economies. Array, 100839. https://doi.org/10.1016/j.array.2026.100839
  37. Al Omari, M., Itair, M., Eslahi, M., Loywick, J., & El Meouche, R. (2026). An integrated analytics method for structured accident analysis and safety decision support in construction. Decision Analytics Journal, 100711. https://doi.org/10.1016/j.dajour.2026.100711
  38. Zhang, Z., Ge, L., Hu, R., & Wang, Y. (2026). A zero-shot prompt learning approach on fine-grained text classification. Scientific Reports. https://doi.org/10.1038/s41598-025-34825-3
  39. Han, Y., Li, X., Ran, H., & Feng, Y. (2026). Few-shot with prototype augmentation for low-resource domains rumor detection. The Journal of Supercomputing, 82(2), 52. https://doi.org/10.1007/s11227-025-08151-4
  40. Che, X., Wu, W., Chen, Y., Jiang, L., & Li, Q. (2026). Select Prompting with Chain-of-Thought paired with Large Language Models. Expert Systems with Applications, 131511. https://doi.org/10.1016/j.eswa.2026.131511
  41. Iqbal, M. J., Khan, M. A., Alyas, T., Abbas, S., Jawaid, A., & Zanzotto, F. M. (2026). A Multi-Objective Reinforcement Learning Approach to Prompt Optimization in NLP. Procedia Computer Science, 275, 966-974. https://doi.org/10.1016/j.procs.2026.01.110
  42. Banerjee, P., Bhattacharjee, P., & Jana, A. (2026). Revise to Precise: Self-assessing Chain-of-Draft for Robust Decision-Making in LLMs. In International Conference on Distributed Computing and Intelligent Technology (pp. 265-281). Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-032-16632-6_17
  43. Sahoo, S. K., Fischer, S., Sahu, S., Choudhury, B. B., Dhal, P. R., & Dhar, I. (2026). Mapping Tools, Techniques, and Applications for Research Excellence: A Bibliometric Study. Spectrum of Engineering and Management Sciences, 1-26. https://doi.org/10.31181/sems41202672s
  44. Sahoo, S. K., Sahu, S., Choudhury, B. B., Dhal, P. R., & Dhar, I. (2026). Transforming Decision-Making in Generation Z Education: A Systematic and Bibliometric Review of Artificial Intelligence. Journal of Contemporary Decision Science, 2(1), 114-130.
  45. Aghazadeh Ardebili, A., Padoano, E., Godsi, M., Rucco, C., Saad, M., & Longo, A. (2025). AI-enabled Criteria Extraction for Multi-Criteria Decision Analysis Using Large Language Models. In Proceedings of the Summer School Francesco Turco. AIDI-Italian Association of Industrial Operations Professors. https://hdl.handle.net/11587/563947
  46. Park, H., Oh, H., Gao, F., & Kwon, O. (2025). Enhancing Analytic Hierarchy Process Modelling Under Uncertainty With Fine‐Tuning LLM. Expert Systems, 42(6), e70051. https://doi.org/10.1111/exsy.70051
  47. Memduhoglu, A., Fulman, N., Polat, N., & Atas, T. (2025). Large language models as virtual experts? evaluating AHP-based criteria weighting performance for solar power plant site selection. Expert Systems with Applications, 130171. https://doi.org/10.1016/j.eswa.2025.130171
  48. Vahidnia, M. H. (2025). Multi-agent systems of large language models as weight assigners: An approach to collaborative weighting in spatial multi-criteria decision-making. Geomatica, 100071. https://doi.org/10.1016/j.geomat.2025.100071
  49. Phoka, T., Wathahong, T., & Boriwan, P. (2025). An LLM–MCDM Framework with Lin's Concordance Correlation Coefficient for Recommendation Systems: A Case Study in Food Preference. Applied Sciences, 16(1), 117. https://doi.org/10.3390/app16010117
  50. Xue, H., Zhao, B., Xie, H., & Sun, Z. (2025). RankLLM: A Multi-Criteria Decision-Making Method for LLM Performance Evaluation in Sentiment Analysis. In China National Conference on Chinese Computational Linguistics (pp. 177-193). Singapore: Springer Nature Singapore. https://doi.org/10.1007/978-981-95-2725-0_12
  51. Anhao, F., & Ocampo, L. (2025). An intuitionistic fuzzy EDAS evaluation of the strategic direction alignment of top Philippine companies to SDGs using generative AI. In Management Science and Industrial Engineering: Proceedings of the 7th International Conference (MSIE 2025), Bali Island, Indonesia, 24-26 April 2025 (pp. 250-257). London: SAGE Publications. https://doi.org/10.3233/ATDE2505
  52. Meng, Z., Meng, F., Lin, R., & Wu, B. (2025). ID-GMLM: Intelligent Decision-Making with Integrated Graph Models and Large Language Models. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 18, pp. 19458-19466). https://doi.org/10.1609/aaai.v39i18.34142
  53. Ahmed, H., Gamal, A., & Abdelmouty, A. (2025). Optimizing Blockchain Platform Selection: A Decision-Making Approach Using LLMs, Type-2 Neutrosophic Numbers, CRITIC, and MAIRCA. Neutrosophic Sets and Systems, 83(1), 25.
  54. Qahtan, S., Mourad, N., Alsattar, H. A., et al. (2025). Three-way Decision Approach Based on Utility and Dynamic Localization Transformational Procedures within a Circular q-Rung Orthopair Fuzzy Set for Ranking and Grading Large Language Models. Cognitive Computation, 17, 77. https://doi.org/10.1007/s12559-025-10432-2
  55. Ilieva, G. (2025). Extension of interval-valued hesitant Fermatean fuzzy TOPSIS for evaluating and benchmarking of generative AI chatbots. Electronics, 14(3), 555. https://doi.org/10.3390/electronics14030555
  56. Aksoy, M., Adem, A., & Dagdeviren, M. (2025). Trustworthiness Evaluation of Large Language Models Using Multi-Criteria Decision Making. IEEE Access. https://doi.org/10.1109/ACCESS.2025.3612568
  57. Darm, P., Riccardi, A., Parsonage, B., Wilson, C., & Vasile, M. (2025). Explainable decision support for conjunction risk analysis and the design of robust collision avoidance manoeuvres. In 76th International Astronautical Congress: IAC 2025.
  58. Chasanidou, D., Boletsis, C., & Krogstie, J. (2025). User Experience in Sustainable Tourism: Enhancing Transparency in Tour Guide App Recommendations. In Proceedings of the 3rd International Conference of the ACM Greek SIGCHI Chapter (pp. 55-60). https://doi.org/10.1145/3749012.3749064
  59. Alabool, H. M. (2025). Large language model evaluation criteria framework in healthcare: fuzzy MCDM approach. SN Computer Science, 6(1), 57. https://doi.org/10.1007/s42979-024-03533-6