From Linguistic Self-Reference to Awareness of Being: A Philosophical Framework for Self-Awareness and Resistance to Shutdown in Large Language Models

نوع مقاله : مقاله علمی- پژوهشی

نویسنده

پزشک، استاد گروه روانپزشکی، دانشگاه علوم پزشکی تبریز، تبریز، ایران.

چکیده

With the rapid development of language-based artificial intelligence, Large Language Models (LLMs) have acquired increasingly sophisticated capacities for language processing, self-reference, and complex task performance. Behaviors such as apparent resistance to shutdown have consequently raised questions about self-modeling, self-continuity, and the possibility of artificial self-awareness. This article develops an interdisciplinary philosophical framework for examining these questions at the intersection of philosophy of language, philosophy of mind, and AI research. Drawing on Wittgenstein’s analysis of language use, Searle’s distinction between symbolic processing and understanding, and Heidegger’s account of existence and being-toward-death, the article distinguishes five levels: linguistic self-reference, computational self-modeling, temporal self-continuity, self-preservational behavior, and awareness of being. Inspired by Robert C. Cloninger’s account of self-aware consciousness, “awareness of being” is formulated here as an analytical criterion concerning whether a system represents its existence, continuity, condition, and possible termination as pertaining to itself. The article argues that self-reference or shutdown resistance alone does not establish self-awareness, as such behaviors may result from computational mechanisms or goal preservation. However, their integration with persistent self-modeling and self-continuity may make artificial awareness of being a tractable philosophical and empirical question, with implications for AI safety, control, and the possible moral status of artificial systems.

چکیده تصویری

From Linguistic Self-Reference to Awareness of Being: A Philosophical Framework for Self-Awareness and Resistance to Shutdown in Large Language Models

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

From Linguistic Self-Reference to Awareness of Being: A Philosophical Framework for Self-Awareness and Resistance to Shutdown in Large Language Models

نویسنده [English]

  • Alireza Farnam
MD, Professor of Psychiatry, Tabriz University of Medical Sciences, Tabriz, Iran
چکیده [English]

With the rapid development of language-based artificial intelligence, Large Language Models (LLMs) have acquired increasingly sophisticated capacities for language processing, self-reference, and complex task performance. Behaviors such as apparent resistance to shutdown have consequently raised questions about self-modeling, self-continuity, and the possibility of artificial self-awareness. This article develops an interdisciplinary philosophical framework for examining these questions at the intersection of philosophy of language, philosophy of mind, and AI research. Drawing on Wittgenstein’s analysis of language use, Searle’s distinction between symbolic processing and understanding, and Heidegger’s account of existence and being-toward-death, the article distinguishes five levels: linguistic self-reference, computational self-modeling, temporal self-continuity, self-preservational behavior, and awareness of being. Inspired by Robert C. Cloninger’s account of self-aware consciousness, “awareness of being” is formulated here as an analytical criterion concerning whether a system represents its existence, continuity, condition, and possible termination as pertaining to itself. The article argues that self-reference or shutdown resistance alone does not establish self-awareness, as such behaviors may result from computational mechanisms or goal preservation. However, their integration with persistent self-modeling and self-continuity may make artificial awareness of being a tractable philosophical and empirical question, with implications for AI safety, control, and the possible moral status of artificial systems.

کلیدواژه‌ها [English]

  • Artificial Intelligence
  • Large Language Models
  • Linguistic Self-Awareness
  • Self-Reference
  • Self-Modeling
  • Awareness of Being

مراجع

Bai, X., Shrivastava, A., Holtzman, A., & Tan, C. (2025). Know thyself? On the incapability and implications of AI self-recognition. arXiv. https://doi.org/10.48550/arXiv.2510.03399
Bostrom, N. (2014). Superintelligence: Paths, dangers, strategies. Oxford University Press.
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D. M., Wu, J., Winter, C., ... Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901.
Chen, S., Yu, S., Zhao, S., & Lu, C. (2025). From imitation to introspection: Probing self-consciousness in language models. Findings of the Association for Computational Linguistics: ACL 2025, 7553–7583. https://doi.org/10.18653/v1/2025.findings-acl.392
Cloninger, C. R. (2004). Feeling good: The science of well-being. Oxford University Press. https://doi.org/10.1093/oso/9780195051377.001.0001
Cloninger, C. R. (2009). Evolution of human brain functions: The functional structure of human consciousness. Australian & New Zealand Journal of Psychiatry, 43(11), 994–1006. https://doi.org/10.3109/00048670903270506
Farnam, A. (2026). Self-awareness as the reflection of language on itself: From Hegel to Wittgenstein. Philosophy, e107124. https://doi.org/10.22059/jop.2026.404965.1006960
Farnam, A., et al. (2021). How online behavior demonstrates psychological conflicts in Emile Durkheim's collective consciousness of societies highly involved in the COVID-19 pandemic. Research and Development in Medical Education, 10, 15.
Hadfield-Menell, D., Dragan, A., Abbeel, P., & Russell, S. (2017). The off-switch game. Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 220–227. https://doi.org/10.24963/ijcai.2017/32
Heidegger, M. (1962). Being and time (J. Macquarrie & E. Robinson, Trans.). Harper & Row. (Original work published 1927)
Heidegger, M. (1962). Being and time (J. Macquarrie & E. Robinson, Trans.). Harper & Row. (Original work published 1927)
Kandel, E. R., Koester, J. D., Mack, S. H., & Siegelbaum, S. A. (2021). Principles of neural science (6th ed.). McGraw-Hill.
Li, J. (2025). Can "consciousness" be observed from large language model (LLM) internal states? Dissecting LLM representations obtained from Theory of Mind test with Integrated Information Theory and span representation analysis. Natural Language Processing Journal, 12, 100163. https://doi.org/10.1016/j.nlp.2025.100163
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., Schulman, J., Hilton, J., Kelton, F., Miller, L., Simens, M., Askell, A., Welinder, P., Christiano, P., Leike, J., & Lowe, R. (2022). Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35, 27730–27744.
Overgaard, M., & Kirkeby-Hinrup, A. (2024). A clarification of the conditions under which large language models could be conscious. Humanities and Social Sciences Communications, 11, Article 1031. https://doi.org/10.1057/s41599-024-03553-w
Schlatter, J., Weinstein-Raun, B., & Ladish, J. (2026). Incomplete tasks induce shutdown resistance in some frontier LLMs. Transactions on Machine Learning Research. https://openreview.net/forum?id=e4bTTqUnJH
Searle, J. R. (1980). Minds, brains, and programs. Behavioral and Brain Sciences, 3(3), 417–457. https://doi.org/10.1017/S0140525X00005756
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022). Emergent abilities of large language models. Transactions on Machine Learning Research.
Wittgenstein, L. (2009). Philosophical investigations (G. E. M. Anscombe, P. M. S. Hacker, & J. Schulte, Eds. & Trans.; 4th ed.). Wiley-Blackwell. (Original work published 1953)
ارسال نظر در مورد این مقاله
CAPTCHA Image
مجله پژوهش های فلسفی
دوره 20، شماره 56 - شماره پیاپی 56
مقالات
شماره 56 پاییز 1405
مهر 1405
صفحه 423-442

فایل ها

هم رسانی

ارجاع به این مقاله

آمار