{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T00:29:28Z","timestamp":1759364968223,"version":"build-2065373602"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3612568","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T17:45:39Z","timestamp":1758563139000},"page":"168183-168201","source":"Crossref","is-referenced-by-count":0,"title":["Trustworthiness Evaluation of Large Language Models Using Multi-Criteria Decision Making"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3232-3923","authenticated-orcid":false,"given":"Meltem","family":"Aksoy","sequence":"first","affiliation":[{"name":"Department of Computer Science, Research Center Trustworthy Data Science and Security of the University Alliance Ruhr, Technical University Dortmund, Dortmund, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4820-6684","authenticated-orcid":false,"given":"Aylin","family":"Adem","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, Gazi University, Ankara, Türkiye"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2121-5978","authenticated-orcid":false,"given":"Metin","family":"Da\u011fdeviren","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, Gazi University, Ankara, Türkiye"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-short.47"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.lindif.2023.102274"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3659048"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.tbench.2025.100204"},{"key":"ref5","article-title":"LLM as an art director (LaDi): Using LLMs to improve text-to-media generators","author":"Roush","year":"2023","journal-title":"arXiv:2311.03716"},{"key":"ref6","article-title":"Evaluating large language models: A comprehensive survey","author":"Guo","year":"2023","journal-title":"arXiv:2310.19736"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.58496\/adsa\/2025\/003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/iccai66501.2025.00076"},{"key":"ref9","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref10","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022","journal-title":"arXiv:2203.02155"},{"key":"ref11","article-title":"Bias in large language models: Origin, evaluation, and mitigation","author":"Guo","year":"2024","journal-title":"arXiv:2411.10915"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/aaai.12188"},{"key":"ref14","article-title":"Challenges in guardrailing large language models for science","author":"Pantha","year":"2024","journal-title":"arXiv:2411.08181"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-63787-2_15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3846\/20294913.2014.892037"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.ssci.2018.02.033"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.31181\/dma1120237"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2007.01.004"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1080\/23311916.2019.1623153"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijpe.2012.03.036"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.11.010"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhydene.2018.08.024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3233\/jifs-179464"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"ref26","first-page":"105","article-title":"TrustLLM: Trustworthiness in large language models","volume-title":"Proc. 41st Int. Conf. Mach. Learn. (ICML)","author":"Sun"},{"key":"ref27","article-title":"Holistic evaluation of language models","author":"Liang","year":"2022","journal-title":"arXiv:2211.09110"},{"key":"ref28","article-title":"DecodingTrust: A comprehensive assessment of trustworthiness in GPT models","author":"Wang","year":"2023","journal-title":"arXiv:2306.11698"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.152"},{"key":"ref30","article-title":"XTRUST: On the multilingual trustworthiness of large language models","author":"Li","year":"2024","journal-title":"arXiv:2409.15762"},{"key":"ref31","first-page":"1","article-title":"Measuring and enhancing trustworthiness of LLMs in RAG through grounded attributions and learning to refuse","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Song"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-024-02090-y"},{"key":"ref33","article-title":"LLM-as-a-fuzzy-judge: Fine-tuning large language models as a clinical evaluation judge with fuzzy logic","author":"Zheng","year":"2025","journal-title":"arXiv:2506.11221"},{"key":"ref34","article-title":"Enhancing multi-criteria decision analysis with AI: Integrating analytic hierarchy process and GPT-4 for automated decision support","author":"Svoboda","year":"2024","journal-title":"arXiv:2402.07404"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.dajour.2023.100168"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-024-03533-6"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2022.104951"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/su15107905"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.35808\/ersj\/3744"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2008.10.016"},{"issue":"21","key":"ref41","first-page":"86","article-title":"MCDM methodologies and applications: A literature review from 1999 to 2009","volume":"21","author":"Eshlaghy","year":"2011","journal-title":"Res. J. Int. Stud."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1080\/18756891.2015.1046325"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113738"},{"issue":"4","key":"ref44","first-page":"4925","article-title":"Analytical hierarchical process (AHP) and fuzzy AHP applications\u2014A review paper","volume":"8","author":"Singh","year":"2016","journal-title":"Int. J. Pharm. Technol."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1108\/00251741011043920"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/0377-2217(90)90057-I"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/1-4020-0611-x_31"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1080\/18756891.2014.964011"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1007\/978-3-642-25664-6_34","article-title":"Hesitant fuzzy linguistic term sets","volume":"122","author":"Herrera","year":"2011","journal-title":"Adv. Intell. Soft Comput."},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3233\/JIFS-179467"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2011.2170076"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06494-6"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/91.890332"},{"volume-title":"Hello GPT-4o","year":"2024","key":"ref54"},{"volume-title":"Introducing ChatGPT","year":"2022","key":"ref55"},{"volume-title":"Introducing Llama 3.1: Our Most Capable Models to Date","year":"2024","key":"ref56"},{"volume-title":"Claude 3.5 Sonnet","year":"2024","key":"ref57"},{"volume-title":"Our Next-Generation Model: Gemini 1.5","year":"2024","author":"Pichai","key":"ref58"},{"volume-title":"Large Enough","year":"2024","key":"ref59"},{"key":"ref60","article-title":"DeepSeek-V3 technical report","volume-title":"arXiv:2412.19437","author":"Liu","year":"2024"},{"volume-title":"ChatBot Arena Leaderboard","year":"2025","key":"ref61"},{"volume-title":"Open LLM Leaderboard","year":"2025","key":"ref62"},{"key":"ref63","article-title":"Trustworthy LLMs: A survey and guideline for evaluating large language models\u2019 alignment","author":"Liu","year":"2023","journal-title":"arXiv:2308.05374"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11174270.pdf?arnumber=11174270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T05:17:00Z","timestamp":1759295820000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11174270\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3612568","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}