{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T23:26:52Z","timestamp":1780961212377,"version":"3.54.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Research Council of Finland through the 6G Flagship program","award":["318927"],"award-info":[{"award-number":["318927"]}]},{"name":"CO2CREATION Strategic Research Council project","award":["372355"],"award-info":[{"award-number":["372355"]}]},{"name":"EC through the HEU NEUROCLIMA project","award":["GA 101137711"],"award-info":[{"award-number":["GA 101137711"]}]},{"DOI":"10.13039\/501100008530","name":"ERDF","doi-asserted-by":"crossref","award":["A81568"],"award-info":[{"award-number":["A81568"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100008530","name":"ERDF","doi-asserted-by":"crossref","award":["A91867"],"award-info":[{"award-number":["A91867"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Business Finland through the Neural pub\/sub research project","award":["8754\/31\/2022"],"award-info":[{"award-number":["8754\/31\/2022"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3686088","type":"journal-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T19:50:24Z","timestamp":1776801024000},"page":"66493-66515","source":"Crossref","is-referenced-by-count":1,"title":["Beyond the Leaderboard: A Survey of the Science of Evaluation, Benchmarking, and Methodologies for Large Language Models"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3600-966X","authenticated-orcid":false,"given":"Saeid","family":"Sheikhi","sequence":"first","affiliation":[{"name":"University of Oulu, Oulu, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9475-4839","authenticated-orcid":false,"given":"Lauri","family":"Lov\u00e9n","sequence":"additional","affiliation":[{"name":"University of Oulu, Oulu, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8545-599X","authenticated-orcid":false,"given":"Panos","family":"Kostakos","sequence":"additional","affiliation":[{"name":"University of Oulu, Oulu, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Artificial Intelligence Risk Management Framework (AI RMF 1.0)","year":"2023"},{"key":"ref2","first-page":"2357","article-title":"MathQA: Towards interpretable math word problem solving with operation-based formalisms","volume-title":"Proc. Conf. North Amer. chapter Assoc. Comput. linguistics, Hum. Lang. Technol.","author":"Amini"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.421"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.401"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2024.21700"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.226"},{"key":"ref7","article-title":"Emergent abilities in large language models: A survey","author":"Berti","year":"2025","journal-title":"arXiv:2503.05788"},{"key":"ref8","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref9","article-title":"Humans or LLMs as the judge? A study on judgement biases","author":"Hardy Chen","year":"2024","journal-title":"arXiv:2402.10669"},{"key":"ref10","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021","journal-title":"arXiv:2107.03374"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.11"},{"key":"ref12","article-title":"A survey on data contamination for large language models","author":"Cheng","year":"2025","journal-title":"arXiv:2502.14425"},{"key":"ref13","article-title":"Think you have solved question answering? Try arc, the AI2 reasoning challenge","author":"Clark","year":"2018","journal-title":"arXiv:1803.05457"},{"key":"ref14","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021","journal-title":"arXiv:2110.14168"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.393"},{"key":"ref17","article-title":"Automatic generation of benchmarks and reliable llm judgment for code tasks","author":"Farchi","year":"2024","journal-title":"arXiv:2410.21071"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-demos.6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/TACL.a.20"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00474"},{"key":"ref21","article-title":"Evaluating large language models: A comprehensive survey","author":"Guo","year":"2023","journal-title":"arXiv:2310.19736"},{"key":"ref22","article-title":"Measuring massive multitask language understanding","author":"Hendrycks","year":"2020","journal-title":"arXiv:2009.03300"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"ref24","volume-title":"P3419\u2014Standard for Large Language Model Evaluation","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3747588"},{"key":"ref26","article-title":"SWE-bench: Can language models resolve real-world GitHub issues?","volume-title":"arXiv:2310.06770","author":"Jimenez","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.324"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.764"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.187"},{"key":"ref30","article-title":"Holistic evaluation of language models","author":"Liang","year":"2022","journal-title":"arXiv:2211.09110"},{"key":"ref31","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"ref33","article-title":"AgentBench: Evaluating LLMs as agents","author":"Liu","year":"2023","journal-title":"arXiv:2308.03688"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref35","article-title":"HarmBench: A standardized evaluation framework for automated red teaming and robust refusal","author":"Mazeika","year":"2024","journal-title":"arXiv:2402.04249"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3640310.3674093"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2197"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3704435"},{"issue":"8","key":"ref40","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00322"},{"key":"ref42","first-page":"55565","article-title":"Are emergent abilities of large language models a mirage?","volume-title":"Proc. Adv. neural Inf. Process. Syst.","volume":"36","author":"Schaeffer"},{"key":"ref43","article-title":"Language models are multilingual chain-of-thought reasoners","author":"Shi","year":"2022","journal-title":"arXiv:2210.03057"},{"issue":"5","key":"ref44","first-page":"1","article-title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models","volume":"2023","author":"Srivastava","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref45","first-page":"3266","article-title":"SuperGLUE: A stickier benchmark for general-purpose language understanding systems","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2866"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC63097.2024.00027"},{"key":"ref49","article-title":"Federated large language models: Current progress and future directions","author":"Yao","year":"2024","journal-title":"arXiv:2409.15723"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijar.2022.09.004"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1472"},{"key":"ref53","article-title":"BERTScore: Evaluating text generation with BERT","author":"Zhang","year":"2019","journal-title":"arXiv:1904.09675"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.830"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref56","article-title":"WebArena: A realistic web environment for building autonomous agents","author":"Zhou","year":"2023","journal-title":"arXiv:2307.13854"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11488866.pdf?arnumber=11488866","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T19:41:00Z","timestamp":1778269260000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11488866\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3686088","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}