20.500.12556/DiRROS-26991 An experimental evaluation of large language models in supporting the DEX multi-criteria decision-making process We experimentally assessed the capabilities of two mainstream artificial intelligence chatbots, ChatGPT and DeepSeek, to support the multi-criteria decision-making process. Specifically, we focused on using the method DEX (Decision EXpert) and investigated their performance in all stages of DEX model development and utilization. The results indicate that these tools may substantially contribute in the difficult stages of collecting and structuring decision criteria, and collecting data about decision alternatives. However, at the current stage of development, the support for the whole multi-criteria decision-making process is still lacking, mainly due to occasionally inconsistent and erroneous execution of methodological steps. To leverage the strengths of both approaches, we also propose a hybrid workflow for DEX model development that begins in the LLM and continues in the specialized DEXiWin software. multi-criteria decision making DEX method decision analysis large language models veliki jezikovni modeli večkriterijsko odločanje analiza odločanja metoda DEX true false true Informatika Slovenija Angleški jezik Slovenski jezik Copyright © Slovenian Society Informatika Neznano 2026-01-28 12:02:53 2026-01-28 12:02:54 2026-01-31 04:11:44 0000-00-00 00:00:00 2025 0 0 Nasl. z nasl. zaslona; Opis vira z dne 28. 1. 2026; str. 633-640 no. 4 Vol. 49 2025 0000-00-00 Zaloznikova Objavljeno NiDoloceno 0000-00-00 0000-00-00 2025-01-12 004.8 1854-3871 10.31449/inf.v49i4.12884 266419971 https://www.informatica.si/index.php/informatica/article/view/12884 1 e7113756-fc38-11f0-a15d-001a4af901a5 https://dirros.openscience.si/Dokument.php?lang=slv&id=39601 RAZ_Bohanec_Marko_2025.pdf RAZ_Bohanec_Marko_2025.pdf 1 C80BC07A90ADD8A458B84AEE300DE713 eb9414d0e3ad2a1319d88d75cdd37f52c6964d6b3101886b2aa0c0f5a49c8f1d 90697b75-fc39-11f0-a15d-001a4af901a5 https://dirros.openscience.si/Dokument.php?lang=slv&id=39603 Institut Jožef Stefan 0 0 0