Identifying features that shape perceived consciousness in LLM-based AI: A quantitative study of human responses
Open accessPublished version of a preprint
Abstract
This study quantitatively examines which features of AI-generated text lead humans to perceive subjective consciousness in large language model (LLM)-based AI systems. Drawing on 99 passages from conversations with AI and focusing on eight features—Metacognitive Self-reflection, Logical Reasoning, Empathy, Emotionality, Knowledge, Fluency, Unexpectedness, and Subjective Expressiveness—we surveyed with 123 participants. Using regression and clustering analyses, we investigated how these features influence participants' perceptions of AI consciousness. The results reveal that metacognitive self-reflection and the AI's expression of its own emotions significantly increased perceived consciousness, while a heavy emphasis on knowledge reduced it. Participants clustered into subgroups, each showing distinct feature-weighting patterns. Additionally, higher prior knowledge of LLMs and more frequent usage of LLM-based chatbots were associated with greater overall likelihood assessments of AI consciousness. This study underscores the multidimensional and individualized nature of perceived AI consciousness and provides a foundation for a better understanding of the psychosocial implications of human-AI interaction.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing
Benjamini, Y., & Hochberg, Y. (1995) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1995.tb02031.x · Cited by 109,482 · see citing works
Intraclass correlations: Uses in assessing rater reliability.
Shrout, P. E., & Fleiss, J. L. (1979) · Psychological Bulletin · doi:10.1037/0033-2909.86.2.420 · Cited by 23,433 · see citing works
Silhouettes: A graphical aid to the interpretation and validation of cluster analysis
Rousseeuw, P. J. (1987) · Journal of Computational and Applied Mathematics · doi:10.1016/0377-0427(87)90125-7 · Cited by 21,392 · see citing works
Metacognition and cognitive monitoring: A new area of cognitive–developmental inquiry
Flavell, J. H. (1979) · American Psychologist · doi:10.1037/0003-066x.34.10.906 · Cited by 11,282 · cited 1× · see citing works
“Metacognition refers to a higher-order cognitive function closely related to self-awareness in humans, allowing individuals to evaluate and regulate their knowledge and learning processes [34].”
I.—COMPUTING MACHINERY AND INTELLIGENCE
TURING, A. M. (1950) · Mind · doi:10.1093/mind/lix.236.433 · Cited by 10,290 · cited 1× · see citing works
“Our methodology may invite comparisons to Turing’s seminal work in 1950 on machine intelligence, as both studies involve human evaluation of machine-generated responses [31].”
Davies, D. L., & Bouldin, D. W. (1979) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.1979.4766909 · Cited by 9,145 · see citing works
A Dendrite Method for Cluster Analysis
Caliński, T., & Harabasz, J. (1974) · Communications in Statistics - Simulation and Computation · doi:10.1080/03610927408827101 · Cited by 7,857 · see citing works
ELIZA—a computer program for the study of natural language communication between man and machine
Weizenbaum, J. (1966) · Communications of the ACM · doi:10.1145/365153.365168 · Cited by 4,452 · see citing works
Gray, H. M., Gray, K., & Wegner, D. M. (2007) · Science · doi:10.1126/science.1134475 · Cited by 2,342 · see citing works
Algorithms for hierarchical clustering: an overview
Murtagh, F., & Contreras, P. (2012) · WIREs Data Mining Knowl. Discov. · doi:10.1002/widm.53 · Cited by 1,982 · see citing works
Who Sees Human?: The Stability and Importance of Individual Differences in Anthropomorphism
Waytz, A., Cacioppo, J., & Epley, N. (2010) · Perspectives on Psychological Science · doi:10.1177/1745691610369336 · Cited by 1,228 · see citing works
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
Tabassi, E. (2023) · doi:10.6028/nist.ai.100-1 · Cited by 1,136 · see citing works
Inventing Temperature: Measurement and Scientific Progress
Chang, H. (2004) · doi:10.1093/0195171276.001.0001 · Cited by 883 · see citing works
Recommendation of the Council on Artificial Intelligence (OECD)
Yeung, K. (2020) · International Legal Materials · doi:10.1017/ilm.2020.5 · Cited by 824 · see citing works
Consciousness: here, there and everywhere?
Tononi, G., & Koch, C. (2015) · Philosophical Transactions of the Royal Society B: Biological Sciences · doi:10.1098/rstb.2014.0167 · Cited by 811 · see citing works
Role play with large language models
Shanahan, M., McDonell, K., & Reynolds, L. (2023) · Nature · doi:10.1038/s41586-023-06647-8 · Cited by 491 · see citing works
Can Machines Think? Interaction and Perspective Taking with Robots Investigated via fMRI
Krach, S., Hegel, F., Wrede, B., Sagerer, G., Binkofski, F., & Kircher, T. T. J. (2008) · PLoS ONE · doi:10.1371/journal.pone.0002597 · Cited by 490 · see citing works
Measuring consciousness: relating behavioural and neurophysiological approaches
Seth, A. K., Dienes, Z., Cleeremans, A., Overgaard, M., & Pessoa, L. (2008) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2008.04.008 · Cited by 458 · cited 1× · see citing works
“At this point, we are reminded of a notable parallel in the history of science [39, 40].”
The role of metacognition in human social interactions
Frith, C. D. (2012) · Philosophical Transactions of the Royal Society B: Biological Sciences · doi:10.1098/rstb.2012.0123 · Cited by 407 · see citing works
Tsuchiya, N., & Adolphs, R. (2007) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2007.01.005 · Cited by 270 · see citing works
Two conceptions of subjective experience
Sytsma, J., & Machery, E. (2010) · Philosophical Studies · doi:10.1007/s11098-009-9439-x · Cited by 213 · see citing works
Jin, S. V., & Youn, S. (2023) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2022.2129277 · Cited by 201 · see citing works
Consciousness in Artificial Intelligence: Insights from the Science of Consciousness
Butlin, P., Long, R., Elmoznino, E., Bengio, Y., Birch, J., Constant, A., Deane, G., Fleming, S. M., Frith, C., Ji, X., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.08708 · Cited by 196 · see citing works
Design patterns for sociality in human-robot interaction
Kahn, P. H., Freier, N. G., Kanda, T., Ishiguro, H., Ruckert, J. H., Severson, R. L., & Kane, S. K. (2008) · ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1145/1349822.1349836 · Cited by 175 · see citing works
Tests for consciousness in humans and beyond
Bayne, T., Seth, A. K., Massimini, M., Shepherd, J., Cleeremans, A., Fleming, S. M., Malach, R., Mattingley, J. B., Menon, D. K., Owen, A. M., et al. (2024) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2024.01.010 · Cited by 163 · cited 1× · see citing works
“Given that today’s LLM-based AI interacts with humans through natural language, identifying the specific cues in AI’s language that prompt humans to attribute consciousness to AI is critical [10].”
Brauner, P., Hick, A., Philipsen, R., & Ziefle, M. (2023) · Frontiers in Computer Science · doi:10.3389/fcomp.2023.1113903 · Cited by 143 · see citing works
Could a Large Language Model be Conscious?
Chalmers, D. J. (2023) · arXiv · doi:10.48550/arxiv.2303.07103 · Cited by 143 · see citing works
A landscape of consciousness: Toward a taxonomy of explanations and implications
Kuhn, R. L. (2024) · Progress in Biophysics and Molecular Biology · doi:10.1016/j.pbiomolbio.2023.12.003 · Cited by 135 · see citing works
Yam, K. C., Tan, T., Jackson, J. C., Shariff, A., & Gray, K. J. (2023) · Management and Organization Review · doi:10.1017/mor.2023.21 · Cited by 128 · see citing works
A Situation Awareness Perspective on Human-AI Interaction: Tensions and Opportunities
Jiang, J., Karran, A. J., Coursaris, C. K., Léger, P., & Beringer, J. (2022) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2022.2093863 · Cited by 123 · see citing works
Wang, Q., Saha, K., Gregori, E., Joyner, D., & Goel, A. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445645 · Cited by 120 · see citing works
How does HCI Understand Human Agency and Autonomy?
Bennett, D., Metatla, O., Roudaut, A., & Mekler, E. D. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580651 · Cited by 111 · see citing works
Złotowski, J. A., Sumioka, H., Nishio, S., Glas, D. F., Bartneck, C., & Ishiguro, H. (2015) · Frontiers in Psychology · doi:10.3389/fpsyg.2015.00883 · Cited by 110 · see citing works
Evidence that logical reasoning depends on conscious processing
DeWall, C. N., Baumeister, R. F., & Masicampo, E. J. (2008) · Consciousness and Cognition · doi:10.1016/j.concog.2007.12.004 · Cited by 110 · see citing works
The feasibility of artificial consciousness through the lens of neuroscience
Aru, J., Larkum, M. E., & Shine, J. M. (2023) · Trends in Neurosciences · doi:10.1016/j.tins.2023.09.009 · Cited by 98 · see citing works
Folk psychological attributions of consciousness to large language models
Colombatto, C., & Fleming, S. M. (2024) · Neuroscience of Consciousness · doi:10.1093/nc/niae013 · Cited by 96 · cited 1× · see citing works
“The perception that AI possesses consciousness is not limited to a few peculiar individuals; according to a recent survey, 67% of respondents believed there is a possibility that ChatGPT has consciousness [4].”
Cohn, M., Pushkarna, M., Olanubi, G. O., Moran, J. M., Padgett, D., Mengesha, Z., & Heldreth, C. (2024) · Extended Abstracts of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613905.3650818 · Cited by 71 · see citing works
Spatola, N., Marchesi, S., & Wykowska, A. (2022) · Frontiers in Robotics and AI · doi:10.3389/frobt.2022.863319 · Cited by 68 · see citing works
Cultural Variation in Attitudes Toward Social Chatbots
Folk, D. P., Wu, C., & Heine, S. J. (2025) · Journal of Cross-Cultural Psychology · doi:10.1177/00220221251317950 · Cited by 56 · see citing works
A five-layer framework for AI governance: integrating regulation, standards, and certification
Agarwal, A., & Nene, M. J. (2025) · Transforming Government People Process and Policy · doi:10.1108/tg-03-2025-0065 · Cited by 56 · see citing works
Cross-Cultural Differences in Comfort with Humanlike Robots
Castelo, N., & Sárváry, M. (2022) · International Journal of Social Robotics · doi:10.1007/s12369-022-00920-y · Cited by 50 · see citing works
Do You Mind? User Perceptions of Machine Consciousness
Scott, A. E., Neumann, D., Niess, J., & Woźniak, P. W. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581296 · Cited by 46 · see citing works
From internal models toward metacognitive AI
Kawato, M., & Cortese, A. (2021) · Biological Cybernetics · doi:10.1007/s00422-021-00904-7 · Cited by 35 · see citing works
A voice without a mouth no more: The neurobiology of language and consciousness
Skipper, J. I. (2022) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2022.104772 · Cited by 31 · see citing works
Dimensions of Consciousness and the Moral Status of Brain Organoids
Boyd, J. L., & Lipshitz, N. (2023) · Neuroethics · doi:10.1007/s12152-023-09538-x · Cited by 26 · see citing works
Sytsma, J. (2014) · WIREs Cognitive Science · doi:10.1002/wcs.1320 · Cited by 20 · see citing works
AI-C2C (conscious to conscience): a governance framework for ethical AI integration
Anthuvan, T., & Maheshwari, K. (2025) · AI and Ethics · doi:10.1007/s43681-025-00736-2 · Cited by 17 · see citing works
Zhou, J., Porat, T., & Zalk, N. V. (2024) · Human Behavior and Emerging Technologies · doi:10.1155/2024/8864909 · Cited by 16 · see citing works
Type of Education Affects Individuals’ Adoption of Intentional Stance Towards Robots: An EEG Study
Roselli, C., Navare, U. P., Ciardo, F., & Wykowska, A. (2023) · International Journal of Social Robotics · doi:10.1007/s12369-023-01073-2 · Cited by 13 · see citing works
Computational MetacognitionPreprint
Cox, M. T., Mohammad, Z., Kondrakunta, S., Gogineni, V. R., Dannenhauer, D., & Larue, O. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2201.12885 · Cited by 12 · see citing works
Baumeister, R. F., Schmeichel, B. J., & DeWall, C. N. (2014) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780199836963.003.0010 · Cited by 11 · see citing works
Determinism and attributions of consciousness
Björnsson, G., & Shepherd, J. (2020) · Philosophical Psychology · doi:10.1080/09515089.2020.1743256 · Cited by 10 · see citing works
Why People Judge Humans Differently from Machines: The Role of Perceived Agency and Experience
Zhang, J., Conway, J., & Hidalgo, C. A. (2023) · IEEE International Conference on Cognitive Infocommunications · doi:10.1109/coginfocom59411.2023.10397474 · Cited by 10 · see citing works
What is (and was) a person? Evidence on historical mind perceptions from natural language
Ash, E., Stammbach, D., & Tobia, K. P. (2023) · Cognition · doi:10.1016/j.cognition.2023.105501 · Cited by 8 · see citing works
Metacognitive AI: Framework and the Case for a Neurosymbolic Approach
Wei, H., Shakarian, P., Lebiere, C. J., Draper, B. A., Krishnaswamy, N., & Nirenburg, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-71170-1_7 · Cited by 7 · see citing works
Survey of Consciousness Theory from Computational PerspectivePreprint
Ding, Z., Wei, X., & Xu, Y. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2309.10063 · Cited by 3 · see citing works
The Epistemic Asymmetry of Consciousness Self-Reports: A Formal Analysis of AI Consciousness DenialPreprint
Kim, C.-E. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.05454 · Cited by 1 · see citing works
Self-citationAI Consciousness and Public Perceptions: Four FuturesPreprint
Fernandez, I., Kyosovska, N., Luong, J., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.04771
Flagged first, then by citations
Cited by
Sorted by citations
Hu, P., Wang, L., Chang, D., Zhu, Z., Chen, Y., Ren, Z., & Dumayi, H. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2605181 · Cited by 3 · see citing works
Attribution of consciousness to non-human animals: insights from AI and multidimensional frameworks
Chiarella, S. G., Laurenzi, M., D'Onofrio, M., Gallagher, S., & Raffone, A. (2026) · Frontiers in Psychology · doi:10.3389/fpsyg.2026.1716363 · Cited by 1 · see citing works
Bariach, B., Schoenegger, P., Bhaskar, M., & Suleyman, M. (2026) · AI and Ethics · doi:10.1007/s43681-026-01294-x · Cited by 1 · see citing works
Are Attributions of Consciousness to AI Chatbots Epistemically Innocent?
Peters, U. (2026) · Minds and Machines · doi:10.1007/s11023-026-09795-8
AI models as consciousness attributors: how LLMs ascribe consciousness to other agents
Kang, B., & Kim, C.-E. (2026) · Frontiers in Psychology · doi:10.3389/fpsyg.2026.1926286
Self-citationSalingaros, N. A., Lavdas, A. Α., & Peña, S. M. (2026) · Buildings · doi:10.3390/buildings16173424
- Authors
- Kang, B., Kim, J., Yun, T., Bae, H., & Kim, C.-E.
- Affiliations
- Gachon University (KR)
- Dongguk University (KR)
- Corresponding author
- Kim, Jundong
- Bae, Hyojin
- Kim, Chang-Eop
- Venue
- Computers in Human Behavior Reports
- Publisher
- Elsevier BV
- Published
- 2026-03
- Volume
- 21
- Pages
- 100901
- ISSN
- 2451-9588 (ISSN-L)
- OpenAlex
- W4417067202
- Cited by
- 6
- References
- 49
- Citations by year
- 2026: 6
- FWCI
- 6.65
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Computers in Human Behavior Reports (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University)
- Funders
- Ministry of Education (RS2024-00453246)
- National Research Foundation of Korea
- Ministry of Science and ICT, South Korea (RS-2024-00339889)
- Topics
- Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Philosophy and Theoretical Science
- Social Sciences › Safety Research › Ethics and Social Impacts of AI
- Keywords
- large language models, AI chatbots, artificial empathy, AI knowledge, unexpectedness, logical reasoning, human-AI interaction, anthropomorphism
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
