{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T22:41:52Z","timestamp":1775083312744,"version":"3.50.1"},"reference-count":68,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>This study investigated whether humans and generative Large Language Models (LLMs) exhibit similar performance in divergent ideation but diverge in convergent selection. To address the critical oversight in current AI creativity research, which predominantly focuses on generative output, this study introduces the original conceptual framework of \u2018Selection Alignment\u2019 and a \u2018novel dual-phase experimental protocol.\u2019 This research transcends traditional generation-centric evaluations to establish a new paradigm for assessing the evaluative stage of creativity. A controlled experiment involved 240 design professionals (120 idea generators, 120 independent selectors) and two LLM agents (GPT-4o, Gemini 1.5 Pro). Participants and LLMs responded to identical divergent prompts, including 10 Alternative Uses Task-style prompts and 10 design problems. Both humans and LLMs generated candidate idea pools, then performed convergent selection by choosing the top five items per prompt. Idea generation was evaluated based on Fluency, Flexibility, and Semantic Breadth. Selection outcomes were compared using top-5 overlap rates derived from semantic clustering. The results indicated near-parity in generation metrics, showing no statistically significant differences between human and AI outputs. However, a substantial divergence was observed in convergent selection: the mean human\u2013AI top-5 overlap was 19.2% for Model-A and 22.4% for Model-B, both significantly below permutation-based chance levels (null mean overlap \u2248 35%). AI selections were strongly predicted by embedding- and probability-based metrics, while human choices were better predicted by context- and experience-based criteria, highlighting a fundamental mechanistic divide. This suggests that convergent selection amplifies human\u2013AI divergence, carrying significant implications for designing co-creative interfaces that integrate human experience into AI\u2019s selection mechanisms.<\/jats:p>","DOI":"10.3390\/info17030243","type":"journal-article","created":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T14:06:56Z","timestamp":1772460416000},"page":"243","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Limits of Computational Selection and Their Implications for Human\u2013AI Divergence in Convergent Creativity"],"prefix":"10.3390","volume":"17","author":[{"given":"Sungwook","family":"Jung","sequence":"first","affiliation":[{"name":"Department of Industrial Design, College of Art and Design, Zhejiang A&F University, Hangzhou 311300, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2814-0847","authenticated-orcid":false,"given":"Ken","family":"Nah","sequence":"additional","affiliation":[{"name":"International Design Trend Center, Hongik University, Seoul 04068, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1017\/S089006041000048X","article-title":"Teaching innovative design reasoning: How concept\u2013knowledge theory can help overcome fixation effects","volume":"25","author":"Hatchuel","year":"2011","journal-title":"Artif. Intell. Eng. Des. Anal. Manuf."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3440","DOI":"10.1038\/s41598-024-53303-w","article-title":"The current state of artificial intelligence generative language models is more creative than humans on divergent thinking tasks","volume":"14","author":"Hubert","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_3","unstructured":"Doshi-Velez, F., and Kim, B. (2017). Towards a Rigorous Science of Interpretable Machine Learning. arXiv."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1515\/CJAL-2023-0206","article-title":"How personal, experiential, and contextual factors mediate EFL teachers\u2019 conceptions of assessment: A narrative study","volume":"46","author":"Xu","year":"2023","journal-title":"Chin. J. Appl. Linguist."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"757","DOI":"10.3758\/s13428-020-01453-w","article-title":"Automating creativity assessment with SemDis: An open platform for computing semantic distance","volume":"53","author":"Beaty","year":"2021","journal-title":"Behav. Res. Methods"},{"key":"ref_6","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention is All you Need. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"26839","DOI":"10.1109\/ACCESS.2024.3365742","article-title":"A Review on Large Language Models: Architectures, Applications, Taxonomies, Open Issues and Challenges","volume":"12","author":"Raiaan","year":"2024","journal-title":"IEEE Access"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zhang, Z., and Yuan, K.H. (2018). Practical Statistical Power Analysis, ISDSA Press.","DOI":"10.35566\/power"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Reimers, N., and Gurevych, I. (2019, January 3\u20137). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China.","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Galli, C., Donos, N., and Calciolari, E. (2024). Performance of 4 Pre-Trained Sentence Transformer Models in the Semantic Query of a Systematic Review Dataset on Peri-Implantitis. Information, 15.","DOI":"10.3390\/info15020068"},{"key":"ref_11","unstructured":"Socolovsky, E.A., and Bushnell, D.M. (2002). A Dissimilarity Measure for Clustering High- and Infinite Dimensional Data That Satisfies the Triangle Inequality, NASA Langley Research Center. NASA\/CR-2002-212136."},{"key":"ref_12","first-page":"67","article-title":"Overview of Agglomerative Hierarchical Clustering Methods","volume":"7","author":"Oti","year":"2024","journal-title":"Br. J. Comput. Netw. Inf. Technol."},{"key":"ref_13","unstructured":"Rahutomo, F., Kitasuka, T., and Aritsugi, M. (2012, January 22\u201323). Semantic cosine similarity. Proceedings of the 7th International Student Conference on Advanced Science and Technology (ICAST 2012), Seoul, Republic of Korea."},{"key":"ref_14","unstructured":"Ester, M., Kriegel, H.-P., Sander, J., and Xu, X. (1996, January 2\u20134). A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise. Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (KDD-96), Portland, OR, USA."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1037\/0033-2909.86.2.420","article-title":"Intraclass correlations: Uses in assessing rater reliability","volume":"86","author":"Shrout","year":"1979","journal-title":"Psychol. Bull."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1177\/001316446002000104","article-title":"A Coefficient of Agreement for Nominal Scales","volume":"20","author":"Cohen","year":"1960","journal-title":"Educ. Psychol. Meas."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1038\/nature13570","article-title":"Limits on fundamental limits to computation","volume":"512","author":"Markov","year":"2014","journal-title":"Nature"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1162\/tacl_a_00638","article-title":"Lost in the Middle: How Language Models Use Long Contexts","volume":"12","author":"Liu","year":"2024","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"ref_19","first-page":"28","article-title":"The generalization of \u2018Student\u2019s\u2019 problem when several different population variances are involved","volume":"34","author":"Welch","year":"1947","journal-title":"Biometrika"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"225","DOI":"10.3758\/PBR.16.2.225","article-title":"Bayesian t tests for accepting and rejecting the null hypothesis","volume":"16","author":"Rouder","year":"2009","journal-title":"Psychon. Bull. Rev."},{"key":"ref_21","unstructured":"Hensher, D.A., and Stopher, P.R. (1979). Quantitative Methods for Analyzing Travel Behaviour of Individuals: Some Recent Developments. Behavioural Travel Modelling, Croom Helm."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2323","DOI":"10.1519\/JSC.0b013e318278eea0","article-title":"The importance of a priori sample size estimation in strength and conditioning research","volume":"27","author":"Beck","year":"2013","journal-title":"J. Strength Cond. Res."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1007\/s10664-025-10625-1","article-title":"Design pattern recognition: A study of large language models","volume":"30","author":"Pandey","year":"2025","journal-title":"Empir. Softw. Eng."},{"key":"ref_24","unstructured":"Tang, X., Zheng, Z., Li, J., Meng, F., Zhu, S.-C., Liang, Y., and Zhang, M. (2024). Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners. arXiv."},{"key":"ref_25","unstructured":"Misra, K., Ettinger, A., and Rayz, J. (2021, January 1\u20136). Do language models learn typicality judgments from text?. Proceedings of the ACL-IJCNLP 2021, Online."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ch\u00e1vez-Autor, J. (2025). Artificial Creativity: From predictive AI to Generative System 3. Front. Artif. Intell., 8.","DOI":"10.3389\/frai.2025.1654716"},{"key":"ref_27","first-page":"399","article-title":"Embodied Design Cognition: Action-Based Formalizations in Architectural Design","volume":"12","author":"Smithwick","year":"2014","journal-title":"Int. J. Archit. Comput."},{"key":"ref_28","first-page":"18","article-title":"Contextual analysis for the design of controlled vocabularies","volume":"33","author":"Mai","year":"2006","journal-title":"Bull. Am. Soc. Inf. Sci. Technol."},{"key":"ref_29","unstructured":"Li, Z. (2008). The Mental Scale in Anchoring Effects: Evidence from Event-Related Potentials. [Master\u2019s Thesis, Beijing Normal University]."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1037\/a0016755","article-title":"Conditions for intuitive expertise: A failure to disagree","volume":"64","author":"Kahneman","year":"2009","journal-title":"Am. Psychol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1017\/pds.2025.10062","article-title":"AI-powered inventive design: Idea funnelling, concept creation, and hybrid problem-solving teams","volume":"5","author":"Livotov","year":"2025","journal-title":"Proc. Des. Soc."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1111\/j.1466-769X.2009.00428.x","article-title":"Professional knowledge and the epistemology of reflective practice","volume":"11","author":"Kinsella","year":"2010","journal-title":"Nurs. Philos."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1177\/030631295025003006","article-title":"The Technical Shaping of Technology: Real-World Constraints and Technical Logic in Edison\u2019s Electrical Lighting System","volume":"25","author":"Vincenti","year":"1995","journal-title":"Soc. Stud. Sci."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1080\/095119299130281","article-title":"Integrated knowledge-based approach and system for product design for assembly","volume":"12","author":"Zha","year":"1999","journal-title":"Int. J. Comput. Integr. Manuf."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3387166","article-title":"A multidisciplinary survey and framework for design and evaluation of explainable AI systems","volume":"11","author":"Mohseni","year":"2021","journal-title":"ACM Trans. Interact. Intell. Syst."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3579612","article-title":"Improving Human-AI Collaboration With Descriptions of AI Behavior","volume":"Volume 7","author":"Cabrera","year":"2023","journal-title":"Proceedings of the ACM on Human-Computer Interaction"},{"key":"ref_37","unstructured":"Johns, C. (2025). Model-Based User Interface Optimization Under Contextual Uncertainty. [Ph.D. Thesis, Aarhus University]."},{"key":"ref_38","first-page":"1","article-title":"Achieving the \u201cAI sweet spot\u201d: Balancing feasibility, viability, and desirability in Artificial Intelligence Implementation","volume":"12","author":"Brugger","year":"2025","journal-title":"Int. J. Econ. Bus. Manag. Stud."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1111\/jpim.12523","article-title":"Innovation and Design in the Age of Artificial Intelligence","volume":"37","author":"Verganti","year":"2020","journal-title":"J. Prod. Innov. Manag."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1007\/s11831-025-10302-y","article-title":"Generative Design for Engineering Applications: A State-of-the-Art Review","volume":"33","author":"Tanveer","year":"2025","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref_41","first-page":"1","article-title":"Interpretable Machine Learning under Evolving Fraud Regimes with Human-in-the-Loop Adaptation","volume":"2","author":"Williams","year":"2025","journal-title":"J. Data Driven Insights"},{"key":"ref_42","unstructured":"Xu, G., Chen, Q., Ling, C., Wang, B., and Shui, C. (2024). Intersectional unfairness discovery. arXiv."},{"key":"ref_43","unstructured":"Khan, H., Khalid, A.F., and Hassan, Z. (2024). Transcending Controlled Environments: Assessing the Transferability of ASR-Robust NLU Models to Real-World Applications. arXiv."},{"key":"ref_44","first-page":"102","article-title":"E2E Process Automation Leveraging Generative AI and IDP-Based Automation Agent: A Case Study on Corporate Expense Processing","volume":"4","author":"Jeong","year":"2025","journal-title":"Artif. Intell. Appl."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Wyllie, S., Shumailov, I., and Papernot, N. (2024, January 3\u20136). Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias. Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency, Rio de Janeiro, Brazil.","DOI":"10.1145\/3630106.3659029"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"58800","DOI":"10.1109\/ACCESS.2025.3556781","article-title":"Responsible AI Framework for Autonomous Vehicles: Addressing Bias and Fairness Risks","volume":"13","author":"Tiwari","year":"2025","journal-title":"IEEE Access"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Roy, A., Raghunandan, D., Elmqvist, N., and Battle, L. (2023, January 3\u20136). How I Met Your Data Science Team: A Tale of Effective Communication. Proceedings of the 2023 IEEE Symposium on Visual Languages and Human-Centric Computing (VL\/HCC), Washington, DC, USA.","DOI":"10.1109\/VL-HCC57772.2023.00032"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Hewett, T., and Meadow, C.T. (1986, January 13\u201317). On designing for usability: An application of four key principles. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI \u201886), Boston, MA, USA.","DOI":"10.1145\/22627.22379"},{"key":"ref_49","unstructured":"Samoili, S., Cobo, M.L., G\u00f3mez, E., De Prato, G., Mart\u00ednez-Plumed, F., and Delipetrev, B. (2020). AI Watch. Defining Artificial Intelligence. Towards an Operational Definition and Taxonomy of Artificial Intelligence, Publications Office of the European Union. EUR 30117 EN."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"2841","DOI":"10.1017\/pds.2025.10298","article-title":"Scenario to specification: Promises and pitfalls of AI in developing user-centered engineering specifications with interdisciplinary teams","volume":"5","author":"Ismatullaev","year":"2025","journal-title":"Proc. Des. Soc."},{"key":"ref_51","first-page":"2382","article-title":"Navigating and reviewing ethical dilemmas in AI development: Strategies for transparency, fairness, and accountability","volume":"5","author":"Akinrinola","year":"2024","journal-title":"Eng. Sci. Technol. J."},{"key":"ref_52","unstructured":"Behrouzi, B., Liu, X., and Tweed, D. (2017). Costate-focused models for reinforcement learning. arXiv."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1038\/s41746-022-00634-5","article-title":"Medical domain knowledge in domain-agnostic generative AI","volume":"5","author":"Kather","year":"2022","journal-title":"npj Digit. Med."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1002\/ev.20556","article-title":"Large language model applications for evaluation: Opportunities and ethical implications","volume":"2023","author":"Head","year":"2023","journal-title":"New Dir. Eval."},{"key":"ref_55","unstructured":"Gu, X., Pang, T., Du, C., Liu, Q., Zhang, F., Du, C., Wang, Y., and Lin, M. (2024). When Attention Sink Emerges in Language Models: An Empirical View. arXiv."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"282","DOI":"10.2307\/357775","article-title":"Cognition, Context, and Theory Building","volume":"40","author":"Flower","year":"1989","journal-title":"Coll. Compos. Commun."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1136\/bmj.330.7500.1121","article-title":"The Gold Standard: Not a Golden Standard","volume":"330","author":"Claassen","year":"2005","journal-title":"BMJ"},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"e25759","DOI":"10.2196\/25759","article-title":"Role of artificial intelligence applications in real-life clinical practice: Systematic review","volume":"23","author":"Yin","year":"2021","journal-title":"J. Med. Internet Res."},{"key":"ref_59","unstructured":"Rezwana, J., and Maher, M.L. (2022). Identifying Ethical Issues in AI Partners in Human-AI Co-Creation. arXiv."},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"Pedreschi, D., Giannotti, F., Guidotti, R., Monreale, A., Ruggieri, S., and Turini, F. (February, January 27). Meaningful explanations of black box AI decision systems. Proceedings of the AAAI 2019, Honolulu, HI, USA.","DOI":"10.1609\/aaai.v33i01.33019780"},{"key":"ref_61","unstructured":"Dai, J., Pan, X., Sun, R., Ji, J., Xu, X., Liu, M., Wang, Y., and Yang, Y. (2024, January 7\u201311). Safe RLHF: Safe Reinforcement Learning from Human Feedback. Proceedings of the 12th International Conference on Learning Representations (ICLR 2024), Vienna, Austria."},{"key":"ref_62","first-page":"15","article-title":"Fostering research data management in collaborative research contexts: Lessons learnt from an \u2018Embedded\u2019 Evaluation of \u201cdata story\u201d","volume":"17","author":"Mosconi","year":"2023","journal-title":"Int. J. Digit. Curation"},{"key":"ref_63","doi-asserted-by":"crossref","unstructured":"Mannava, M.K. (2024, January 12\u201313). Causal Inference in AI Based Decision Support: Beyond Correlation to Causation. Proceedings of the 2024 4th International Conference on Ubiquitous Computing and Intelligent Information Systems (ICUIS), Gobichettipalayam, India.","DOI":"10.1109\/ICUIS64676.2024.10866582"},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1109\/TPC.2012.2206190","article-title":"Combining Concurrent Think-Aloud Protocols and Eye-Tracking Observations: An Analysis of Verbalizations and Silences","volume":"55","author":"Elling","year":"2012","journal-title":"IEEE Trans. Prof. Commun."},{"key":"ref_65","doi-asserted-by":"crossref","unstructured":"Borghoff, U.M., Bottoni, P., and Pareschi, R. (2025). Beyond Prompt Chaining: The tb-cspn Architecture for Agentic AI. Future Internet, 17.","DOI":"10.20944\/preprints202507.1294.v1"},{"key":"ref_66","unstructured":"Park, C., Liu, M., Kong, D., Zhang, K., and Ozdaglar, A. (2024, January 21\u201327). RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation. Proceedings of the 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria."},{"key":"ref_67","first-page":"154","article-title":"Human-AI Co-Design and Co-Creation: A Review of Emerging Approaches, Challenges, and Future Directions","volume":"4","author":"Kadenhe","year":"2025","journal-title":"AAAI Spring Symp. Ser."},{"key":"ref_68","unstructured":"Cai, H., Cai, X., Chang, J., Li, S., Yao, L., Wang, C., Gao, Z., Wang, H., Li, Y., and Lin, M. (2024, January 16\u201321). SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis. Proceedings of the NAACL-HLT 2024, Mexico City, Mexico."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/3\/243\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T14:22:11Z","timestamp":1772461331000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/3\/243"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,2]]},"references-count":68,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["info17030243"],"URL":"https:\/\/doi.org\/10.3390\/info17030243","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,2]]}}}