{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T17:01:34Z","timestamp":1780506094057,"version":"3.54.1"},"reference-count":55,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T00:00:00Z","timestamp":1754352000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>As organizations increasingly seek to leverage machine learning (ML) capabilities, the technical complexity of implementing ML solutions creates significant barriers to adoption and impacts operational efficiency. This research examines how Large Language Models (LLMs) can transform the accessibility of ML technologies within organizations through a human-centered Automated Machine Learning (AutoML) approach. Through a comprehensive user study involving 15 professionals across various roles and technical backgrounds, we evaluate the organizational impact of an LLM-based AutoML framework compared to traditional implementation methods. Our research offers four significant contributions to both management practice and technical innovation: First, we present pioneering evidence that LLM-based interfaces can dramatically improve ML implementation success rates, with 93.34% of users achieved superior performance in the LLM condition, with 46.67% showing higher accuracy (10%\u201325% improvement over baseline) and 46.67% demonstrating significantly higher accuracy (&amp;gt;25% improvement over baseline), while 6.67% maintained comparable performance levels; and 60% reporting substantially reduced development time. Second, we demonstrate how natural language interfaces can effectively bridge the technical skills gap in organizations, cutting implementation time by 50% while improving accuracy across all expertise levels. Third, we provide valuable insights for organizations designing human-AI collaborative systems, showing that our approach reduced error resolution time by 73% and significantly accelerated employee learning curves. Finally, we establish empirical support for natural language as an effective interface for complex technical systems, offering organizations a path to democratize ML capabilities without compromising quality or performance.<\/jats:p>","DOI":"10.3389\/frai.2025.1590105","type":"journal-article","created":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T14:24:17Z","timestamp":1754403857000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Evaluation of large language model-driven AutoML in data and model management from human-centered perspective"],"prefix":"10.3389","volume":"8","author":[{"given":"Jiapeng","family":"Yao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lantian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiping","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,8,5]]},"reference":[{"key":"B1","article-title":"Gradio: Hassle-free sharing and testing of ml models in the wild","author":"Abid","year":"2019","journal-title":"arXiv preprint arXiv:1906.02569"},{"key":"B2","author":"Allal","year":"2023"},{"key":"B3","article-title":"Program synthesis with large language models","author":"Austin","year":"2021","journal-title":"arXiv preprint arXiv:2108.07732"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10462-024-10726-1","article-title":"Automated machine learning: past, present and future","volume":"57","author":"Baratchi","year":"2024","journal-title":"Artif. Intell. Rev"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-73263-1","author":"Brazdil","year":"2008","journal-title":"Metalearning: Applications to Data Mining"},{"key":"B6","doi-asserted-by":"publisher","first-page":"7675","DOI":"10.55214\/25768484.v8i6.3676","article-title":"Collaborative automated machine learning (automl) process framework","volume":"8","author":"Chami","year":"2024","journal-title":"Edelweiss Appl. Sci. Technol"},{"key":"B7","article-title":"A survey on evaluating large language models in code generation tasks","author":"Chen","year":"","journal-title":"arXiv preprint arXiv:2408.16498"},{"key":"B8","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021","journal-title":"arXiv preprint arXiv:2107.03374"},{"key":"B9","first-page":"285","article-title":"\u201cLlm2automl: zero-code automl framework leveraging large language models,\u201d","volume-title":"2024 International Conference on Intelligent Robotics and Automatic Control (IRAC)","author":"Chen","year":""},{"key":"B10","article-title":"Is functional correctness enough to evaluate code language models? Exploring diversity of generated codes","author":"Chon","year":"2024","journal-title":"arXiv preprint arXiv:2408.14504"},{"key":"B11","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","article-title":"\u201cImagenet: a large-scale hierarchical image database,\u201d","volume-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","author":"Deng","year":"2009"},{"key":"B12","article-title":"Autogluon-tabular: Robust and accurate automl for structured data","author":"Erickson","year":"2020","journal-title":"arXiv preprint arXiv:2003.06505"},{"key":"B13","article-title":"\u201cEfficient and robust automated machine learning,\u201d","author":"Feurer","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90","article-title":"\u201cDeep residual learning for image recognition,\u201d","author":"He","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B15","first-page":"754","article-title":"\u201cAn efficient approach for assessing hyperparameter importance,\u201d","volume-title":"International Conference on Machine Learning","author":"Hutter","year":"2014"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5","author":"Hutter","year":"2019","journal-title":"Automated Machine Learning: Methods, Systems, Challenges"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330648","article-title":"\u201cAuto-keras: an efficient neural architecture search system,\u201d","author":"Jin","year":"2019","journal-title":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery &Data Mining"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580919","article-title":"\u201cStudying the effect of AI code generators on supporting novice learners in introductory programming,\u201d","author":"Kazemitabaar","year":"2023","journal-title":"Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems"},{"key":"B19","doi-asserted-by":"publisher","first-page":"3487","DOI":"10.1109\/TMI.2023.3288940","article-title":"Artifact detection and restoration in histology images with stain-style and structural preservation","volume":"42","author":"Ke","year":"","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B20","first-page":"260","article-title":"\u201cA high-throughput tumor location system with deep learning for colorectal cancer histopathology image,\u201d","volume-title":"International Conference on Artificial Intelligence in Medicine","author":"Ke","year":""},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1145\/3397391.3397442","article-title":"\u201cA prediction model of microsatellite status from histology images,\u201d","author":"Ke","year":"","journal-title":"Proceedings of the 2020 10th International Conference on Biomedical Engineering and Technology"},{"key":"B22","doi-asserted-by":"publisher","first-page":"107520","DOI":"10.1016\/j.cmpb.2023.107520","article-title":"Mine local homogeneous representation by interaction information clustering with unsupervised learning in histopathology images","volume":"235","author":"Ke","year":"","journal-title":"Comput. Methods Progr. Biomed"},{"key":"B23","article-title":"\u201cH2o automl: Scalable automatic machine learning,\u201d","volume-title":"Proceedings of the AutoML Workshop at ICML","author":"LeDell","year":"2020"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00371-024-03608-8","article-title":"Toward the unification of generative and discriminative visual foundation model: a survey","volume":"2024","author":"Liu","year":"","journal-title":"Visual Comput"},{"key":"B25","article-title":"Autoproteinengine: a large language model driven agent framework for multimodal automl in protein engineering","author":"Liu","year":"","journal-title":"arXiv preprint arXiv:2411.04440"},{"key":"B26","first-page":"5395","article-title":"\u201cToursynbio-search: a large language model driven agent framework for unified search method for protein engineering,\u201d","volume-title":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","author":"Liu","year":""},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680665","article-title":"\u201cAutom3l: an automated multimodal machine learning framework with large language models,\u201d","author":"Luo","year":"2024","journal-title":"Proceedings of the 32nd ACM International Conference on Multimedia"},{"key":"B28","first-page":"95","article-title":"\u201cLearning to predict the optimal template in stain normalization for histology image analysis,\u201d","volume-title":"International Conference on Artificial Intelligence in Medicine","author":"Luo","year":"2024"},{"key":"B29","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1109\/BRACIS.2016.018","article-title":"\u201cHyper-parameter tuning of a decision tree induction algorithm,\u201d","volume-title":"2016 5th Brazilian Conference on Intelligent Systems (BRACIS)","author":"Mantovani","year":"2016"},{"key":"B30","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1109\/AITest62860.2024.00022","article-title":"\u201cUser centric evaluation of code generation tools,\u201d","volume-title":"2024 IEEE International Conference on Artificial Intelligence Testing (AITest)","author":"Miah","year":"2024"},{"key":"B31","first-page":"66","article-title":"\u201cTpot: a tree-based pipeline optimization tool for automating machine learning,\u201d","volume-title":"Workshop on Automatic Machine Learning","author":"Olson","year":"2016"},{"key":"B32","first-page":"1","article-title":"\u201cAutomatic machine learning: an exploratory review,\u201d","volume-title":"2021 9th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions)","author":"Patibandla","year":"2021"},{"key":"B33","first-page":"4095","article-title":"\u201cEfficient neural architecture search via parameters sharing,\u201d","volume-title":"International Conference on Machine Learning","author":"Pham","year":"2018"},{"key":"B34","doi-asserted-by":"crossref","first-page":"1051","DOI":"10.1109\/ICDM.2017.137","article-title":"\u201cInforming the use of hyperparameter optimization through metalearning,\u201d","volume-title":"2017 IEEE International Conference on Data Mining (ICDM)","author":"Sanders","year":"2017"},{"key":"B35","first-page":"1","article-title":"\u201cKnowledgeie: unifying online-offline distillation based on knowledge inheritance and evolution,\u201d","volume-title":"2024 International Joint Conference on Neural Networks (IJCNN)","author":"Shen","year":"2024"},{"key":"B36","first-page":"2382","article-title":"\u201cToursynbio: a multi-modal large model and agent framework to bridge text and protein sequences for protein engineering,\u201d","volume-title":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","author":"Shen","year":""},{"key":"B37","first-page":"205","article-title":"\u201cMovit: memorizing vision transformers for medical image analysis,\u201d","volume-title":"International Workshop on Machine Learning in Medical Imaging","author":"Shen","year":"2023"},{"key":"B38","first-page":"81","article-title":"\u201cPromptable counterfactual diffusion model for unified brain tumor segmentation and generation with mris,\u201d","volume-title":"International Workshop on Foundation Models for General Medical AI","author":"Shen","year":""},{"key":"B39","article-title":"Operating room workflow analysis via reasoning segmentation over digital twins","author":"Shen","year":"","journal-title":"arXiv preprint arXiv:2503.21054"},{"key":"B40","first-page":"542","article-title":"\u201cFastsam3d: an efficient segment anything model for 3D volumetric medical images,\u201d","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Shen","year":""},{"key":"B41","article-title":"Online reasoning video segmentation with just-in-time digital twins","author":"Shen","year":"","journal-title":"arXiv preprint arXiv:2503.21056"},{"key":"B42","first-page":"373","article-title":"\u201cProteinengine: empower LLM with domain knowledge for protein engineering,\u201d","volume-title":"International Conference on Artificial Intelligence in Medicine","author":"Shen","year":""},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01164","article-title":"\u201cSelf-distillation from the last mini-batch for consistency regularization,\u201d","author":"Shen","year":"2022","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170","article-title":"\u201cRecursive deep models for semantic compositionality over a sentiment treebank,\u201d","author":"Socher","year":"2013","journal-title":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581082","article-title":"\u201cAutoml in the wild: obstacles, workarounds, and expectations,\u201d","author":"Sun","year":"2023","journal-title":"Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems"},{"key":"B46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10664-025-10614-4","article-title":"Bugs in large language models generated code: an empirical study","volume":"30","author":"Tambon","year":"2025","journal-title":"Empir. Softw. Eng"},{"key":"B47","article-title":"Automl-agent: a multi-agent llm framework for full-pipeline automl","author":"Trirat","year":"2024","journal-title":"arXiv preprint arXiv:2410.02958"},{"key":"B48","article-title":"Automl-GPT: large language model for automl","author":"Tsai","year":"2023","journal-title":"arXiv preprint arXiv:2309.01125"},{"key":"B49","first-page":"81","article-title":"\u201cHistology image artifact restoration with lightweight transformer based diffusion model,\u201d","volume-title":"International Conference on Artificial Intelligence in Medicine","author":"Wang","year":"2024"},{"key":"B50","doi-asserted-by":"publisher","first-page":"4584","DOI":"10.3390\/electronics13234584","article-title":"Evaluating causal reasoning capabilities of large language models: a systematic analysis across three scenarios","volume":"13","author":"Wang","year":"2024","journal-title":"Electronics"},{"key":"B51","first-page":"1","article-title":"\u201cDiffimpute: tabular data imputation with denoising diffusion probabilistic model,\u201d","volume-title":"2024 IEEE International Conference on Multimedia and Expo (ICME)","author":"Wen","year":"2024"},{"key":"B52","article-title":"Large language models meet nl2code: a survey","author":"Zan","year":"2022","journal-title":"arXiv preprint arXiv:2212.09420"},{"key":"B53","article-title":"Automl-gpt: Automatic machine learning with gpt","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2305.02499"},{"key":"B54","doi-asserted-by":"publisher","first-page":"3079","DOI":"10.1109\/TPAMI.2021.3067763","article-title":"Auto-pytorch: multi-fidelity metalearning for efficient and robust autodl","volume":"43","author":"Zimmer","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B55","article-title":"Neural architecture search with reinforcement learning","author":"Zoph","year":"2016","journal-title":"arXiv preprint arXiv:1611.01578"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1590105\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T22:06:08Z","timestamp":1754517968000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1590105\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,5]]},"references-count":55,"alternative-id":["10.3389\/frai.2025.1590105"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1590105","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,5]]},"article-number":"1590105"}}