{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T17:42:02Z","timestamp":1773250922976,"version":"3.50.1"},"reference-count":53,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T00:00:00Z","timestamp":1736208000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Chung-Ang University Research Grants in 2024","award":["RS-2024-00337250"],"award-info":[{"award-number":["RS-2024-00337250"]}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT)","doi-asserted-by":"publisher","award":["RS-2024-00337250"],"award-info":[{"award-number":["RS-2024-00337250"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Axioms"],"abstract":"<jats:p>This paper introduces a mathematical framework for defining and quantifying self-identity in artificial intelligence (AI) systems, addressing a critical gap in the theoretical foundations of artificial consciousness. While existing approaches to artificial self-awareness often rely on heuristic implementations or philosophical abstractions, we present a formal framework grounded in metric space theory, measure theory, and functional analysis. Our framework posits that self-identity emerges from two mathematically quantifiable conditions: the existence of a connected continuum of memories C\u2286M in a metric space (M,dM), and a continuous mapping I:M\u2192S that maintains consistent self-recognition across this continuum, where (S,dS) represents the metric space of possible self-identities. To validate this theoretical framework, we conducted empirical experiments using the Llama 3.2 1B model, employing low-rank adaptation (LoRA) for efficient fine-tuning. The model was trained on a synthetic dataset containing temporally structured memories, designed to capture the complexity of coherent self-identity formation. Our evaluation metrics included quantitative measures of self-awareness, response consistency, and linguistic precision. The experimental results demonstrate substantial improvements in measurable self-awareness metrics, with the primary self-awareness score increasing from 0.276 to 0.801 (190.2% improvement) after fine-tuning. In contrast to earlier methods that view self-identity as an emergent trait, our framework introduces tangible metrics to assess and measure artificial self-awareness. This enables the structured creation of AI systems with validated self-identity features. The implications of our study are immediately relevant to the fields of humanoid robotics and autonomous systems. Additionally, it opens up new prospects for controlled adjustments of self-identity in contexts that demand different levels of personal involvement. Moreover, the mathematical underpinning of our framework serves as the basis for forthcoming investigations into AI, linking theoretical models to real-world applications in current AI technologies.<\/jats:p>","DOI":"10.3390\/axioms14010044","type":"journal-article","created":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T05:06:34Z","timestamp":1736226394000},"page":"44","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Emergence of Self-Identity in Artificial Intelligence: A Mathematical Framework and Empirical Study with Generative Large Language Models"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2562-172X","authenticated-orcid":false,"given":"Minhyeok","family":"Lee","sequence":"first","affiliation":[{"name":"School of Electrical and Electronics Engineering, Chung-Ang University, Seoul 06974, Republic of Korea"}]}],"member":"1968","published-online":{"date-parts":[[2025,1,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1093\/logcom\/exh034","article-title":"Logic, self-awareness and self-improvement: The metacognitive loop and the problem of brittleness","volume":"15","author":"Anderson","year":"2005","journal-title":"J. Log. Comput."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Greenwood, N., Sundaram, B., Muirhead, A., and Copperthwaite, J. (2020, January 17\u201321). Awareness without Neural Networks: Achieving Self-Aware AI via Evolutionary and Adversarial Processes. Proceedings of the 2020 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C), Washington, DC, USA.","DOI":"10.1109\/ACSOS-C51401.2020.00047"},{"key":"ref_3","unstructured":"Lee, M. (2024). Is Polarization an Inevitable Outcome of Similarity-Based Content Recommendations?\u2014Mathematical Proofs and Computational Validation. arXiv."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1047","DOI":"10.1109\/JPROC.2020.2977722","article-title":"Self-aware neural network systems: A survey and new perspective","volume":"108","author":"Du","year":"2020","journal-title":"Proc. IEEE"},{"key":"ref_5","unstructured":"Lee, M. (2024). Does Low Spoilage Under Cold Conditions Foster Cultural Complexity During the Foraging Era?\u2014A Theoretical and Computational Inquiry. arXiv."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Metzinger, T. (2004). Being No One: The Self-Model Theory of Subjectivity, MIT Press.","DOI":"10.7551\/mitpress\/1551.001.0001"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Sporns, O., Tononi, G., and K\u00f6tter, R. (2005). The human connectome: A structural description of the human brain. PLoS Comput. Biol., 1.","DOI":"10.1371\/journal.pcbi.0010042"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1109\/JPROC.2020.2990784","article-title":"Self-awareness for autonomous systems","volume":"108","author":"Dutt","year":"2020","journal-title":"Proc. IEEE"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"987","DOI":"10.1109\/JPROC.2020.2986602","article-title":"Multisensorial generative and descriptive self-awareness models for autonomous systems","volume":"108","author":"Regazzoni","year":"2020","journal-title":"Proc. IEEE"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Wang, C., and Peng, K. (2023). AI experience predicts identification with humankind. Behav. Sci., 13.","DOI":"10.3390\/bs13020089"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Kouros, T., and Papa, V. (2024). Digital Mirrors: AI Companions and the Self. Societies, 14.","DOI":"10.3390\/soc14100200"},{"key":"ref_12","unstructured":"Zeng, Y., Zhao, F., Zhao, Y., Zhao, D., Lu, E., Zhang, Q., Wang, Y., Feng, H., Zhao, Z., and Wang, J. (2024). Brain-inspired and Self-based Artificial Intelligence. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Lai, J.W. (2024). Adapting Self-Regulated Learning in an Age of Generative Artificial Intelligence Chatbots. Future Internet, 16.","DOI":"10.3390\/fi16060218"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Oberg, A. (2023). Souls and Selves: Querying an AI Self with a View to Human Selves and Consciousness. Religions, 14.","DOI":"10.3390\/rel14010075"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1080\/17405629.2021.1890578","article-title":"Self-recognition and emotional knowledge","volume":"19","author":"Lewis","year":"2022","journal-title":"Eur. J. Dev. Psychol."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Pelivani, E., and Cico, B. (2021, January 16\u201317). Toward self-aware machines: Insights of causal reasoning in artificial intelligence. Proceedings of the 2021 International Conference on Information Technologies (InfoTech), Varna, Bulgaria.","DOI":"10.1109\/InfoTech52438.2021.9548511"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"103652","DOI":"10.1016\/j.robot.2020.103652","article-title":"Self-awareness in intelligent vehicles: Feature based dynamic Bayesian models for abnormality detection","volume":"134","author":"Kanapram","year":"2020","journal-title":"Robot. Auton. Syst."},{"key":"ref_18","unstructured":"Meta AI (2024). Llama 3.2: Revolutionizing edge AI and vision with open, customizable models. Technical Report, Meta AI."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Gerlich, M. (2023). Perceptions and acceptance of artificial intelligence: A multi-dimensional study. Soc. Sci., 12.","DOI":"10.3390\/socsci12090502"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ionescu, C.G., and Licu, M. (2023). Are TikTok algorithms influencing users\u2019 self-perceived identities and personal values? A mini review. Soc. Sci., 12.","DOI":"10.3390\/socsci12080465"},{"key":"ref_21","unstructured":"Li, L., and Li, C. (2024). Enabling self-identification in intelligent agent: Insights from computational psychoanalysis. arXiv."},{"key":"ref_22","unstructured":"Tulving, E. (1983). Elements of Episodic Memory, Oxford University Press."},{"key":"ref_23","unstructured":"Lewis, M., Haviland-Jones, J.M., and Barrett, L.F. (2010). Handbook of Emotions, Guilford Press."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1146\/annurev.ps.41.020190.002221","article-title":"Personality structure: Emergence of the five-factor model","volume":"41","author":"Digman","year":"1990","journal-title":"Annu. Rev. Psychol."},{"key":"ref_25","first-page":"114","article-title":"Paradigm shift to the integrative big five trait taxonomy","volume":"3","author":"John","year":"2008","journal-title":"Handb. Personal. Theory Res."},{"key":"ref_26","unstructured":"Baumeister, R.F. (1999). The Self in Social Psychology, Psychology Press."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1111\/j.1745-6916.2006.00010.x","article-title":"Reciprocal effects of self-concept and performance from a multidimensional perspective: Beyond seductive pleasure and unidimensional perspectives","volume":"1","author":"Marsh","year":"2006","journal-title":"Perspect. Psychol. Sci."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1037\/1089-2680.5.2.100","article-title":"The psychology of life stories","volume":"5","author":"McAdams","year":"2001","journal-title":"Rev. Gen. Psychol."},{"key":"ref_29","unstructured":"Lilienfeld, S.O., Lynn, S.J., Ruscio, J., and Beyerstein, B.L. (2009). 50 Great Myths of Popular Psychology: Shattering Widespread Misconceptions About Human Behavior, John Wiley & Sons."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1279","DOI":"10.1126\/science.1192788","article-title":"How to grow a mind: Statistics, structure, and abstraction","volume":"331","author":"Tenenbaum","year":"2011","journal-title":"Science"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Sugden, R. (1989). Nonlinear Preference and Utility Theory, Oxford University Press.","DOI":"10.2307\/2234100"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"811","DOI":"10.1002\/wcs.79","article-title":"Bayesian models of cognition","volume":"1","author":"Chater","year":"2010","journal-title":"Wiley Interdiscip. Rev. Cogn. Sci."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Parfit, D. (1987). Reasons and Persons, Oxford University Press.","DOI":"10.1093\/019824908X.001.0001"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1016\/j.tics.2010.06.002","article-title":"Letting structure emerge: Connectionist and dynamical systems approaches to cognition","volume":"14","author":"McClelland","year":"2010","journal-title":"Trends Cogn. Sci."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1006\/jmps.2001.1388","article-title":"A distributed representation of temporal context","volume":"46","author":"Howard","year":"2002","journal-title":"J. Math. Psychol."},{"key":"ref_36","unstructured":"Norouzi, M., Fleet, D.J., and Salakhutdinov, R.R. (2012, January 3\u20136). Hamming distance metric learning. Proceedings of the 25th International Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Barto, A.G. (2013). Intrinsic motivation and reinforcement learning. Intrinsically Motivated Learning in Natural and Artificial Systems, Springer.","DOI":"10.1007\/978-3-642-32375-1_2"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1109\/TAMD.2010.2056368","article-title":"Formal theory of creativity, fun, and intrinsic motivation (1990\u20132010)","volume":"2","author":"Schmidhuber","year":"2010","journal-title":"IEEE Trans. Auton. Ment. Dev."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Chatila, R., Renaudo, E., Andries, M., Chavez-Garcia, R.O., Luce-Vayrac, P., Gottstein, R., Alami, R., Clodic, A., Devin, S., and Girard, B. (2018). Toward self-aware robots. Front. Robot. AI, 5.","DOI":"10.3389\/frobt.2018.00088"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1171","DOI":"10.1214\/009053607000000677","article-title":"Kernel methods in machine learning","volume":"36","author":"Hofmann","year":"2008","journal-title":"Ann. Statist."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Rabinovich, M.I., Friston, K.J., and Varona, P. (2012). Principles of brain dynamics, MIT Press Cambridge.","DOI":"10.7551\/mitpress\/9108.001.0001"},{"key":"ref_42","unstructured":"Hinton, G. (2015). Distilling the Knowledge in a Neural Network. arXiv."},{"key":"ref_43","unstructured":"Bishop, C.M. (2006). Pattern Recognition and Machine Learning, Springer."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1038\/nature14541","article-title":"Probabilistic machine learning and artificial intelligence","volume":"521","author":"Ghahramani","year":"2015","journal-title":"Nature"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick","year":"2017","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_46","unstructured":"Guo, C., Pleiss, G., Sun, Y., and Weinberger, K.Q. (2017, January 6\u201311). On calibration of modern neural networks. Proceedings of the International Conference on Machine Learning, Sydney, Australia."},{"key":"ref_47","unstructured":"Finn, C., Abbeel, P., and Levine, S. (2017, January 6\u201311). Model-agnostic meta-learning for fast adaptation of deep networks. Proceedings of the International Conference on Machine Learning, Sydney, Australia."},{"key":"ref_48","unstructured":"Leary, M.R., and Tangney, J.P. (2011). Handbook of Self and Identity, Guilford Press."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.1016\/j.biopsych.2010.12.014","article-title":"Is our self nothing but reward?","volume":"69","author":"Northoff","year":"2011","journal-title":"Biol. Psychiatry"},{"key":"ref_50","first-page":"20675","article-title":"Self-aware personalized federated learning","volume":"35","author":"Chen","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_51","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., and Chen, W. (2021). Lora: Low-rank adaptation of large language models. arXiv."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"450","DOI":"10.1038\/nrn.2016.44","article-title":"Integrated information theory: From consciousness to its physical substrate","volume":"17","author":"Tononi","year":"2016","journal-title":"Nat. Rev. Neurosci."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Li, J., and Mao, H. (2022). The Difficulties in Symbol Grounding Problem and the Direction for Solving It. Philosophies, 7.","DOI":"10.3390\/philosophies7050108"}],"container-title":["Axioms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-1680\/14\/1\/44\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T10:24:10Z","timestamp":1759919050000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-1680\/14\/1\/44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,7]]},"references-count":53,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,1]]}},"alternative-id":["axioms14010044"],"URL":"https:\/\/doi.org\/10.3390\/axioms14010044","relation":{},"ISSN":["2075-1680"],"issn-type":[{"value":"2075-1680","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,7]]}}}