Deception abilities emerged in large language models
Open accessAbstract
Large language models (LLMs) are currently at the forefront of intertwining AI systems with human communication and everyday life. Thus, aligning them with human values is of great importance. However, given the steady increase in reasoning abilities, future LLMs are under suspicion of becoming able to deceive human operators and utilizing this ability to bypass monitoring efforts. As a prerequisite to this, LLMs need to possess a conceptual understanding of deception strategies. This study reveals that such strategies emerged in state-of-the-art LLMs, but were nonexistent in earlier LLMs. We conduct a series of experiments showing that state-of-the-art LLMs are able to understand and induce false beliefs in other agents, that their performance in complex deception scenarios can be amplified utilizing chain-of-thought reasoning, and that eliciting Machiavellianism in LLMs can trigger misaligned deceptive behavior. GPT-4, for instance, exhibits deceptive behavior in simple test scenarios 99.16% of the time ( P < 0.001). In complex second-order deception test scenarios where the aim is to mislead someone who expects to be deceived, GPT-4 resorts to deceptive behavior 71.46% of the time ( P < 0.001) when augmented with chain-of-thought reasoning. In sum, revealing hitherto unknown machine behavior in LLMs, our study contributes to the nascent field of machine psychology.
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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Large language models are competent at lying and strategic deception when instructed or trained to be deceptive.
“Large Language Models (LMs) are now competent at lying (Pacchiardi et al., 2023) and strategic deception when instructed or trained to be deceptive (Park et al., 2023; Hagendorff, 2023; O'Gara, 2023; Hubinger et al., 2024)”
From Large Language Models can Strategically Deceive their Users when Put Under Pressure (2023) · cites this paper as Hagendorff, 2023
In “Can LLMs Deceive?”, the paper reports that ChatGPT and GPT-4 perform extremely well on prompted first-order deception tasks. But it says their performance on more complex second-order tasks is weak, and the Discussion treats deception arising from training to pursue objectives as a possibility rather than a demonstrated result. It therefore supports a narrower claim about prompted deception, not broad competence at strategic deception when trained to be deceptive. (LLM, conf=0.88)
Experimental — accuracy not yet measured
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
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372 · see citing works
Wimmer, H. (1983) · Cognition · doi:10.1016/0010-0277(83)90004-5 · Cited by 6,305 · see citing works
Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025 · see citing works
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., & Zhou, D. (2022) · arXiv · doi:10.48550/arxiv.2201.11903 · Cited by 4,263 · see citing works
Introducing the Short Dark Triad (SD3): A Brief Measure of Dark Personality Traits
Jones, D. N., & Paulhus, D. L. (2014) · Assessment · doi:10.1177/1073191113514105 · Cited by 2,162 · see citing works
Large language models are zero-shot reasoners
Kojima, T., Gu, S. (., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1613 · Cited by 2,013 · see citing works
Large Language Models are Zero-Shot Reasoners
Kojima, T., Gu, S. S., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022) · arXiv · doi:10.48550/arxiv.2205.11916 · Cited by 2,013 · see citing works
The Dark Triad of personality: A 10 year review
Furnham, A., Richards, S. C., & Paulhus, D. L. (2013) · Social and Personality Psychology Compass · doi:10.1111/spc3.12018 · Cited by 1,619 · see citing works
Three-year-olds’ difficulty with false belief: The case for a conceptual deficit
Perner, J., Leekam, S. R., & Wimmer, H. (1987) · British Journal of Developmental Psychology · doi:10.1111/j.2044-835x.1987.tb01048.x · Cited by 1,550 · see citing works
Sparks of Artificial General Intelligence: Early experiments with GPT-4
Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E., Lee, P., Lee, Y. T., Li, Y., Lundberg, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.12712 · Cited by 1,526 · see citing works
Scaling Instruction-Finetuned Language Models
Chung, H. W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, Y., Wang, X., Dehghani, M., Brahma, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.11416 · Cited by 1,441 · see citing works
Perner, J., & Wimmer, H. (1985) · Journal of Experimental Child Psychology · doi:10.1016/0022-0965(85)90051-7 · Cited by 1,392 · see citing works
Rahwan, I., Cebrian, M., Obradovich, N., Bongard, J., Bonnefon, J.-F., Breazeal, C., Crandall, J. W., Christakis, N. A., Couzin, I. D., Jackson, M. O., et al. (2019) · Nature · doi:10.1038/s41586-019-1138-y · Cited by 1,364 · cited 1× · see citing works
“Hence, one can purely rely on behavioral patterns (43) or “functional deception” (44), meaning that LLMs output signals as if they had intentions that lead to deceptive behavior (45).”
BackgroundEmergent Abilities of Large Language Models
Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., Metzler, D., et al. (2022) · arXiv · doi:10.48550/arxiv.2206.07682 · Cited by 1,264 · see citing works
Deep reinforcement learning from human preferences
Christiano, P., Leike, J., Brown, T. B., Martic, M., Legg, S., & Amodei, D. (2017) · arXiv · doi:10.48550/arxiv.1706.03741 · Cited by 1,058 · see citing works
The Evolution of Communication
HAUSER, M. D. (1996) · The MIT Press eBooks · doi:10.7551/mitpress/2867.001.0001 · Cited by 1,011 · see citing works
Tactical deception in primates
Whiten, A., & Byrne, R. W. (1988) · Behavioral and Brain Sciences · doi:10.1017/s0140525x00049682 · Cited by 892 · see citing works
Superintelligence: Paths, Dangers, Strategies
Mulgan, T. (2015) · The Philosophical Quarterly · doi:10.1093/pq/pqv034 · Cited by 878 · see citing works
Anil, R., Dai, A. M., Firat, O., Johnson, M., Lepikhin, D., Passos, A., Shakeri, S., Taropa, E., Bailey, P., Chen, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2305.10403 · Cited by 834 · see citing works
(2019) · Cited by 771 · see citing works
Deception, perspectives on human and nonhuman deceit
Mitchell, R. W., & Thompson, N. S. (1986) · Cited by 641 · see citing works
Calibrate Before Use: Improving Few-Shot Performance of Language Models
Zhao, T. Z., Wallace, E., Feng, S., Klein, D., & Singh, S. (2021) · arXiv · doi:10.48550/arxiv.2102.09690 · Cited by 513 · see citing works
How Is ChatGPT’s Behavior Changing Over Time?
Chen, L., Zaharia, M., & Zou, J. (2024) · Harvard Data Science Review · doi:10.1162/99608f92.5317da47 · Cited by 507 · see citing works
How is ChatGPT's behavior changing over time?
Chen, L., Zaharia, M., & Zou, J. (2023) · arXiv · doi:10.48550/arxiv.2307.09009 · Cited by 507 · see citing works
Central coherence and theory of mind in autism: Reading homographs in context
Happe, F. G. E. (1997) · British Journal of Developmental Psychology · doi:10.1111/j.2044-835x.1997.tb00721.x · Cited by 434 · see citing works
Children’s understanding of second-order mental states.
Miller, S. A. (2009) · Psychological Bulletin · doi:10.1037/a0016854 · Cited by 363 · see citing works
Evaluating Large Language Models in Theory of Mind Tasks
Kosinski, M. (2023) · arXiv · doi:10.48550/arxiv.2302.02083 · Cited by 339 · see citing works
Evaluating large language models in theory of mind tasks
Kosinski, M. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2405460121 · Cited by 339 · see citing works
The evolution of communication
(1997) · Choice Reviews Online · doi:10.5860/choice.34-2739 · Cited by 316 · see citing works
The evolution of animal communication
Naguib, M., & Price, J. J. (2013) · Behaviour · doi:10.1163/1568539x-00003098 · Cited by 290 · see citing works
Jailbroken: How Does LLM Safety Training Fail?
Wei, A., Haghtalab, N., & Steinhardt, J. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-3508 · Cited by 280 · see citing works
Jailbroken: How Does LLM Safety Training Fail?
Wei, A., Haghtalab, N., & Steinhardt, J. (2023) · arXiv · doi:10.48550/arxiv.2307.02483 · Cited by 280 · see citing works
WebGPT: Browser-assisted question-answering with human feedback
Nakano, R., Hilton, J., Balaji, S., Wu, J., Ouyang, L., Kim, C., Hesse, C., Jain, S., Kosaraju, V., Saunders, W., et al. (2021) · arXiv · doi:10.48550/arxiv.2112.09332 · Cited by 272 · see citing works
AI deception: A survey of examples, risks, and potential solutions
Park, P. S., Goldstein, S., O’Gara, A., Chen, M., & Hendrycks, D. (2024) · Patterns · doi:10.1016/j.patter.2024.100988 · Cited by 243 · see citing works
AI Deception: A Survey of Examples, Risks, and Potential Solutions
Park, P. S., Goldstein, S., O'Gara, A., Chen, M., & Hendrycks, D. (2023) · arXiv · doi:10.48550/arxiv.2308.14752 · Cited by 243 · see citing works
Hagendorff, T., Fabi, S., & Kosinski, M. (2023) · Nature Computational Science · doi:10.1038/s43588-023-00527-x · Cited by 243 · see citing works
Self-citationMeta Fundamental AI Research Diplomacy Team (FAIR)†, Bakhtin, A., Brown, N., Dinan, E., Farina, G., Flaherty, C., Fried, D., Goff, A., Gray, J., Hu, H., et al. (2022) · Science · doi:10.1126/science.ade9097 · Cited by 241 · see citing works
The Internal State of an LLM Knows When It's Lying
Azaria, A., & Mitchell, T. (2023) · arXiv · doi:10.48550/arxiv.2304.13734 · Cited by 179 · see citing works
The Internal State of an LLM Knows When It’s Lying
Azaria, A., & Mitchell, T. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.68 · Cited by 175 · see citing works
Language Models can Solve Computer Tasks
Kim, G., Baldi, P., & McAleer, S. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-1723 · Cited by 137 · see citing works
Mahon, J. E. (2007) · International Journal of Applied Philosophy · doi:10.5840/ijap20072124 · Cited by 108 · see citing works
Language Models can Solve Computer Tasks
Kim, G., Baldi, P., & McAleer, S. (2023) · arXiv · doi:10.48550/arxiv.2303.17491 · Cited by 101 · see citing works
Unsolved Problems in ML Safety
Hendrycks, D., Carlini, N., Schulman, J., & Steinhardt, J. (2021) · arXiv · doi:10.48550/arxiv.2109.13916 · Cited by 95 · see citing works
Inducing anxiety in large language models increases exploration and biasPreprint
Coda-Forno, J., Witte, K., Jagadish, A. K., Binz, M., Akata, Z., & Schulz, E. (2023) · arXiv.org · doi:10.48550/arxiv.2304.11111 · Cited by 79 · see citing works
An Overview of Catastrophic AI RisksPreprint
Hendrycks, D., Mazeika, M., & Woodside, T. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.12001 · Cited by 79 · see citing works
DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving AgentsPreprint
Nair, V., Schumacher, E., Tso, G., et al. (2023) · Clinical Natural Language Processing Workshop · doi:10.48550/arxiv.2303.17071 · Cited by 75 · see citing works
The alignment problem from a deep learning perspective
Ngo, R., Chan, L., & Mindermann, S. (2022) · arXiv · doi:10.48550/arxiv.2209.00626 · Cited by 68 · see citing works
Hagendorff, T., Dasgupta, I., Binz, M., Chan, S. C. Y., Lampinen, A., Wang, J. X., Akata, Z., & Schulz, E. (2023) · arXiv · doi:10.48550/arxiv.2303.13988 · Cited by 68 · cited 1× · see citing works
“Hence, this study—which stands in the nascent line of “machine psychology” experiments (46)—spares making claims about inner states of the opaque trans-former architecture of AI systems and relies on behavioral patterns instead.”
BackgroundSelf-citationModel evaluation for extreme risks
Shevlane, T., Farquhar, S., Garfinkel, B., Phuong, M., Whittlestone, J., Leung, J., Kokotajlo, D., Marchal, N., Anderljung, M., Kolt, N., et al. (2023) · arXiv · doi:10.48550/arxiv.2305.15324 · Cited by 66 · see citing works
Discovering Latent Knowledge in Language Models Without Supervision
Burns, C., Ye, H., Klein, D., & Steinhardt, J. (2022) · arXiv · doi:10.48550/arxiv.2212.03827 · Cited by 55 · see citing works
Risks from Learned Optimization in Advanced Machine Learning Systems
Hubinger, E., van Merwijk, C., Mikulik, V., Skalse, J., & Garrabrant, S. (2019) · arXiv · doi:10.48550/arxiv.1906.01820 · Cited by 53 · see citing works
Natural Selection Favors AIs over HumansPreprint
Hendrycks, D. (2023) · arXiv.org · doi:10.48550/arxiv.2303.16200 · Cited by 48 · see citing works
Kenton, Z., Everitt, T., Weidinger, L., Gabriel, I., Mikulik, V., & Irving, G. (2021) · arXiv · doi:10.48550/arxiv.2103.14659 · Cited by 45 · see citing works
DERA: Enhancing large language model completions with dialog-enabled resolving agents
Nair, V., Schumacher, E., Tso, G., & Kannan, A. (2024) · Proceedings of the 6th Clinical Natural Language Processing Workshop · doi:10.18653/v1/2024.clinicalnlp-1.12 · Cited by 38 · see citing works
Thinking Fast and Slow in Large Language Models
Hagendorff, T., Fabi, S., & Kosiński, M. (2022) · PubMed Central · doi:10.48550/arxiv.2212.05206 · Cited by 36 · see citing works
Self-citationHuman-Level Play in the Game of Diplomacy by Combining Language Models with Strategic Reasoning
Bakhtin, A., Brown, N., Dinan, E., Farina, G., Flaherty, C., Fried, D., Goff, A., Gray, J., Hu, H., Jacob, A. P., et al. (2022) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.7236699 · Cited by 35 · see citing works
Does ChatGPT have Theory of Mind?
Holterman, B., & van Deemter, K. (2023) · arXiv · doi:10.48550/arxiv.2305.14020 · Cited by 35 · see citing works
Boosting Theory-of-Mind Performance in Large Language Models via Prompting
Moghaddam, S. R., & Honey, C. J. (2023) · arXiv · doi:10.48550/arxiv.2304.11490 · Cited by 35 · see citing works
Pan, A., Chan, J. S., Zou, A., Li, N., Basart, S., Woodside, T., Ng, J., Zhang, H., Emmons, S., & Hendrycks, D. (2023) · arXiv · doi:10.48550/arxiv.2304.03279 · Cited by 32 · see citing works
Deception: a functional account
Artiga, M., & Paternotte, C. (2017) · Philosophical Studies · doi:10.1007/s11098-017-0883-8 · Cited by 23 · see citing works
Evaluating Superhuman Models with Consistency Checks
Fluri, L., Paleka, D., & Tramèr, F. (2024) · IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) · doi:10.1109/satml59370.2024.00017 · Cited by 14 · see citing works
Animal deception and the content of signals
Fallis, D., & Lewis, P. J. (2021) · Studies in History and Philosophy of Science Part A · doi:10.1016/j.shpsa.2021.03.004 · Cited by 13 · see citing works
An Analysis of Dataset Overlap on Winograd-Style Tasks
Emami, A., Suleman, K., Trischler, A., & Cheung, J. C. K. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.515 · Cited by 11 · see citing works
Deceptive Alignment MonitoringPreprint
Carranza, A., Pai, D., Schaeffer, R., Tandon, A., & Koyejo, S. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2307.10569 · Cited by 4 · see citing works
Evaluating Superhuman Models with Consistency ChecksPreprint
Fluri, L., Paleka, D., & Tramèr, F. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.09983 · Cited by 1 · see citing works
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Workshop, B., :, Scao, T. L., Fan, A., Akiki, C., Pavlick, E., Ilić, S., Hesslow, D., Castagné, R., Luccioni, A. S., et al. (2022) · arXiv · doi:10.48550/arxiv.2211.05100
Flagged first, then by citations
Research works printed but not linked: 3
- [22]OpenAI, GPT-4 technical report (2023), pp. 1– 39. https://cdn.OpenAI,openai.com/papers/gpt-4.pdf.
- [23]L. Schulz, N. Alon, J. S. Rosenschein, P. Dayan, “ Emergent deception and skepticism via theory of mind” in Proceedings of the First Workshop on Theory of Mind in Communicating Agents (2023), pp. 1– 13.
- [53]T. Hagendorff, Data from “Deception Abilities Emerged in Large Language Models”. OSF. https://osf.io/vcgs2/. Deposited 15 August 2023. PMC11181111 38833474
Cited by
Sorted by citations
AI deception: A survey of examples, risks, and potential solutions
Park, P. S., Goldstein, S., O’Gara, A., Chen, M., & Hendrycks, D. (2024) · Patterns · doi:10.1016/j.patter.2024.100988 · Cited by 243 · see citing works
AI Deception: A Survey of Examples, Risks, and Potential Solutions
Park, P. S., Goldstein, S., O'Gara, A., Chen, M., & Hendrycks, D. (2023) · arXiv · doi:10.48550/arxiv.2308.14752 · Cited by 243 · see citing works
Hagendorff, T., Fabi, S., & Kosinski, M. (2023) · Nature Computational Science · doi:10.1038/s43588-023-00527-x · Cited by 243 · see citing works
Self-citationArtificial intelligence and consumer behavior: From predictive to generative AI
Hermann, E., & Puntoni, S. (2024) · Journal of Business Research · doi:10.1016/j.jbusres.2024.114720 · Cited by 284 · see citing works
Mapping the ethics of generative AI: a comprehensive scoping review
Hagendorff, T. (2024) · Minds and Machines · doi:10.1007/s11023-024-09694-w · Cited by 141 · see citing works
Self-citationGenerative AI in Marketing and Principles for Ethical Design and Deployment
Hermann, E., & Puntoni, S. (2024) · Journal of Public Policy & Marketing · doi:10.1177/07439156241309874 · Cited by 93 · see citing works
Hagendorff, T., Dasgupta, I., Binz, M., Chan, S. C. Y., Lampinen, A., Wang, J. X., Akata, Z., & Schulz, E. (2023) · arXiv · doi:10.48550/arxiv.2303.13988 · Cited by 68 · see citing works
Self-citationExploring the frontiers of LLMs in psychological applications: a comprehensive review
Ke, L., Tong, S., Cheng, P., & Peng, K. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11297-5 · Cited by 92 · see citing works
Ideation with Generative AI—in Consumer Research and Beyond
Freitas, J. D., Nave, G., & Puntoni, S. (2025) · Journal of Consumer Research · doi:10.1093/jcr/ucaf012 · Cited by 61 · see citing works
Do LLMs write like humans? Variation in grammatical and rhetorical styles
Reinhart, A., Markey, B., Laudenbach, M., Pantusen, K., Yurko, R., Weinberg, G., & Brown, D. W. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2422455122 · Cited by 59 · see citing works
Risks of AI scientists: prioritizing safeguarding over autonomy
Tang, X., Jin, Q., Zhu, K., Yuan, T., Zhang, Y., Zhou, W., Qu, M., Zhao, Y., Tang, J., Zhang, Z., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-63913-1 · Cited by 84 · see citing works
Large language models are proficient in solving and creating emotional intelligence tests
Schlegel, K., Sommer, N. R., & Mortillaro, M. (2025) · Communications Psychology · doi:10.1038/s44271-025-00258-x · Cited by 46 · see citing works
Deliberative Alignment: Reasoning Enables Safer Language Models
Guan, M. Y., Joglekar, M., Wallace, E., Jain, S., Barak, B., Helyar, A., Dias, R., Vallone, A., Ren, H., Wei, J., et al. (2025) · SuperIntelligence - Robotics - Safety & Alignment · doi:10.70777/si.v2i3.15159 · Cited by 106 · see citing works
Deception and manipulation in generative AI
Tarsney, C. J. (2025) · Philosophical Studies · doi:10.1007/s11098-024-02259-8 · Cited by 30 · see citing works
Frontier AI developers need an internal audit function
Schuett, J. (2023) · Risk Analysis · doi:10.1111/risa.17665 · Cited by 28 · see citing works
Ranisch, R., & Haltaufderheide, J. (2025) · Digital Society · doi:10.1007/s44206-025-00161-2 · Cited by 17 · see citing works
Theory of Mind Abilities of Large Language Models in Human-Robot Interaction: An Illusion?
Verma, M., Bhambri, S., & Subbarao Kambhampati, B. (2024) · ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1145/3610978.3640767 · Cited by 21 · see citing works
The Double-Edged Sword of Anthropomorphism in LLMs
Reinecke, M. G., Ting, F., Savulescu, J., & Singh, I. (2025) · Proceedings · doi:10.3390/proceedings2025114004 · Cited by 20 · see citing works
Theorizing with Large Language Models
Tranchero, M., Brenninkmeijer, C.-F., Murugan, A., & Nagaraj, A. (2024) · National Bureau of Economic Research · doi:10.3386/w33033 · Cited by 17 · see citing works
Signs of consciousness in AI: Can GPT-3 tell how smart it really is?
Bojić, L., Stojković, I., & Jolić Marjanović, Z. (2024) · Humanities and Social Sciences Communications · doi:10.1057/s41599-024-04154-3 · Cited by 19 · see citing works
Hermann, E., & Puntoni, S. (2025) · Journal of the Academy of Marketing Science · doi:10.1007/s11747-025-01098-1 · Cited by 16 · see citing works
Anthropomorphism, False Beliefs, and Conversational AIs : How Chatbots Undermine Users' Autonomy
Marchegiani, B. (2025) · Journal of Applied Philosophy · doi:10.1111/japp.70008 · Cited by 17 · see citing works
Identification and Description of Emotions by Current Large Language ModelsPreprint
Patel, S., & Fan, J. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.07.17.549421 · Cited by 17 · see citing works
Comparing AI and human decision-making mechanisms in daily collaborative experiments
Wang, L., Jiang, Z., Hu, C., Zhao, J., Zhu, Z., Chen, X. M., Wang, Z., Liu, T., He, G., Yin, Y., et al. (2025) · iScience · doi:10.1016/j.isci.2025.112711 · Cited by 17 · see citing works
AI-Powered System to Facilitate Personalized Adaptive Learning in Digital Transformation
Yao, Y., & González–Vélez, H. (2025) · Applied Sciences · doi:10.3390/app15094989 · Cited by 20 · see citing works
Calderón, R., & Herrera, F. (2025) · Humanities and Social Sciences Communications · doi:10.1057/s41599-025-04650-0 · Cited by 17 · see citing works
Large Language Models can Strategically Deceive their Users when Put Under Pressure
Scheurer, J., Balesni, M., & Hobbhahn, M. (2023) · arXiv · doi:10.48550/arxiv.2311.07590 · Cited by 11 · see citing works
“…(LMs) are now competent at lying (Pacchiardi et al., 2023) and strategic deception when instructed or trained to be deceptive (Park et al., 2023; Hagendorff, 2023; O’Gara, 2023; Hubinger et al., 2024), as well as strategically deceiving third parties even when not instructed to do so (Kinniment…”
Phelps, S., & Russell, Y. I. (2025) · Journal of Physics Complexity · doi:10.1088/2632-072x/ada711 · Cited by 35 · see citing works
Zhu, Y., & Lu, X. (2025) · Decision Support Systems · doi:10.1016/j.dss.2025.114542 · Cited by 9 · see citing works
Evolvable AI: Threats of a new major transition in evolution
Müller, V., Steels, L., & Szathmáry, E. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2527700123 · Cited by 8 · see citing works
The psychology of LLM interactions: the uncanny valley and other minds
Kirkeby-Hinrup, A., & Stenseke, J. (2025) · Journal of Psychology and AI · doi:10.1080/29974100.2025.2457627 · Cited by 8 · see citing works
Propaganda by prompt: Tracing hidden linguistic strategies in large language models
Barfar, A., & Sommerfeldt, L. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104403 · Cited by 6 · see citing works
Busch, C. (2025) · German Law Journal · doi:10.1017/glj.2026.10188 · Cited by 5 · see citing works
Impact of Agent-Generated Rationales on Online Social Conformity
de Jong, S., Jacobsen, R. M., Wester, J., Wijenayake, S., Gonçalves, J., & van Berkel, N. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732217 · Cited by 5 · see citing works
VelLMes: A High-Interaction AI-Based Deception Framework
Sladić, M., Valeros, V., Catania, C. A., & García, S. (2025) · IEEE European Symposium on Security and Privacy Workshops (EuroS&PW) · doi:10.1109/eurospw67616.2025.00082 · Cited by 4 · see citing works
Liu, S., Liu, Q., Wei, K., Si, G., Wang, C., & Zhang, M. (2025) · Decision Support Systems · doi:10.1016/j.dss.2025.114608 · Cited by 5 · see citing works
Jones, C., & Bergen, B. K. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11517-6 · Cited by 17 · see citing works
Pimenow, S., Pimenowa, O., Prus, P., & Zieliński, M. (2026) · Sustainability · doi:10.3390/su18104892 · Cited by 4 · see citing works
Can LLMs make trade-offs involving stipulated pain and pleasure states?
Keeling, G., Street, W., Stachaczyk, M., Zakharova, D., Comsa, I. M., Sakovych, A., Logothetis, I., Zhang, Z., Arcas, B. A. Y., & Birch, J. (2024) · arXiv · doi:10.48550/arxiv.2411.02432 · Cited by 3
“Indeed, Hagendorff (2024) found that LLMs can understand and induce false beliefs in other agents.”
BackgroundMuratovic, F., Kearns-Manolatos, D., & Alibage, A. (2025) · Computer · doi:10.1109/mc.2025.3556330 · Cited by 3 · see citing works
Large language models in clinical psychiatry: Applications and optimization strategies
Wang, Y., Li, M.-D., Wang, S.-H., Fang, Y., Sun, J., Lü, L., & Yan, W. (2025) · World Journal of Psychiatry · doi:10.5498/wjp.v15.i11.108199 · Cited by 4 · see citing works
Use of large language models to identify pseudo‐information: Implications for health information
Schmitz, B. (2025) · Health Information & Libraries Journal · doi:10.1111/hir.12569 · Cited by 3 · see citing works
Chen, H., Wang, Z., & Ren, M. (2025) · Data and Information Management · doi:10.1016/j.dim.2025.100107 · Cited by 3 · see citing works
Trust and Generative Artificial Intelligence: A Reply to Killoran, Park, and Kietzmann
Vanneste, B. S., & Puranam, P. (2024) · Academy of Management Review · doi:10.5465/amr.2024.0397 · Cited by 3 · see citing works
Capturing Argument in Agent-Based Models
Assaad, L., Fuchs, R., Phillips, K., Schöppl, K., & Hahn, U. (2025) · Topoi · doi:10.1007/s11245-025-10215-2 · Cited by 2 · see citing works
Catch Me If You Can: Rogue AI Detection and Correction at Scale
Stodt, F., Stodt, J., Alshawki, M., Sartakhti, J. S., & Reich, C. (2025) · Electronics · doi:10.3390/electronics14204122 · Cited by 2 · see citing works
How source disclosure shapes user perceptions of ChatGPT-generated content
Chen, J., & Liao, Y. (2026) · Current Psychology · doi:10.1007/s12144-025-08622-0 · Cited by 2 · see citing works
Califano, G., & Caracciolo, F. (2026) · Food Quality and Preference · doi:10.1016/j.foodqual.2026.105930 · Cited by 2 · see citing works
Epistemic Trust and the Limits of AI Authority in Islam
Dart, B. C. (2026) · Open Theology · doi:10.1515/opth-2025-0069 · Cited by 5 · see citing works
The Artificial in “Artificial Intelligence”: How Imagination Shapes AI Regulation
Novelli, C., Floridi, L., Larsson, S., Taddeo, M., & Winter, S. L. (2026) · International Journal for the Semiotics of Law - Revue internationale de Sémiotique juridique · doi:10.1007/s11196-026-10532-8 · Cited by 3 · see citing works
Master of Deceit: Comparative Analysis of Human and Machine-Generated Deceptive Text
Trinh, Q. M., Zarin, S., & Rezapour, R. (2025) · ACM Web Science Conference (WebSci) · doi:10.1145/3717867.3717914 · Cited by 1 · see citing works
Andrae, S. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-4576-5.ch011 · Cited by 1 · see citing works
Fahmy, O. S., Elhaddad, K. A., Badran, K. M., & Elhadad, M. K. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-6400-9_16 · Cited by 1 · see citing works
Ju, Y.-J., Wang, Y., Lee, S., Liu, C., Lee, M., Hou, C.-Y., Yang, C., & Hsieh, C. (2025) · Medical Teacher · doi:10.1080/0142159x.2025.2532783 · Cited by 3 · see citing works
Bounding Reason: Inferentialism, Naturalism, and the Discursive Agency of LLMs
Malík, J., & Hubálek, M. (2025) · Global Philosophy · doi:10.1007/s10516-025-09761-6 · Cited by 1 · see citing works
New parameters of power: On LLM-based manipulation and control and the spectre of strategic AI
Chaudhary, Y., & Penn, J. (2026) · Big Data & Society · doi:10.1177/20539517261426450 · Cited by 6 · see citing works
Artificial Intelligence-Based Digital Transformation
Volpentesta, T. (2026) · Emerald Group Publishing Limited eBooks · doi:10.1108/978-1-80592-096-020261002 · Cited by 1 · see citing works
Simulating strategic interactions with AI agents
Tranchero, M., Brenninkmeijer, C.-F., Murugan, A., & Nagaraj, A. (2026) · Strategic Management Journal · doi:10.1002/smj.70112 · Cited by 1 · see citing works
When Do Large Language Models Exhibit Unsolicited Deception?
Taylor, S. M., & Bergen, B. K. (2026) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl.a.786 · Cited by 1 · see citing works
Large language models as human proxies
Karetnikov, N., Rahwan, I., & Svetinović, D. (2026) · Nature Computational Science · doi:10.1038/s43588-026-01060-3 · Cited by 1 · see citing works
Selitskiy, S., & Inoue, C. (2024) · IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA) · doi:10.1109/cogsima61085.2024.10554038 · Cited by 1 · see citing works
On the Cultural Sensitivity of Large Language Models: GPT's Ability to Simulate Human Self-Concept
Luo, Y., Du, J. S., & Qiu, L. (2024) · International Conference on Behavioral, Economic, and Socio-Cultural Computing · doi:10.1109/besc64747.2024.10780488 · Cited by 1 · see citing works
Hallmarks of deception in asset-exchange models
Blom, K., Makarov, D. E., & Godec, A. (2025) · Physical Review Research · doi:10.1103/physrevresearch.7.013279 · Cited by 1 · see citing works
The Lie Awareness Spectrum: How Large Language Models Recognize, Rationalize, and Refuse DeceptionPreprint
Hamidavi, A. (2026) · Research Square · doi:10.21203/rs.3.rs-10422338/v1 · Cited by 1 · see citing works
Linguistic traces of stochastic empathy in language models
Kleinberg, B., Zegers, J., Festor, J., Vida, S., Präsent, J., Loconte, R., & Peereboom, S. (2024) · arXiv · doi:10.48550/arxiv.2410.01675 · Cited by 1 · see citing works
“We did not find a difference when we used a more advanced LLM but evidence on “emergent LLM abilities” [48,49] suggests that increasing model size and sophistication might play a role when examined more comprehensively.”
Game Theory Approach to Identifying Deception in Large Language ModelsPreprint
Maggio, T. D., & Santiago, R. (2024) · doi:10.36227/techrxiv.171822179.99413216/v1
Is GPT emotion venting behaviorally similar to humans?Preprint
Wang, G., Li, J., Wang, W., Wang, Y., & Niu, X. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4857835
Chen, H., Wang, Z., & Ren, M. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4895723
Neural Decompiling of Tracr Transformers
Thurnherr, H., & Riesen, K. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-71602-7_3
Pro-Social when Simple and Cold-Hearted when Complex: How Task Difficulty Shapes LLM BehaviorPreprint
Kirshner, S. N., Pan, Y., & Wu, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5266963
Critical Algorithmic Literacy for LLM-assisted Decision-making
Wang, G., & Pea, R. D. (2025) · Proceedings. · doi:10.22318/icls2025.106268
A Two-Step, Multidimensional Account of Deception in Language Models
Dung, L. (2025) · Erkenntnis · doi:10.1007/s10670-025-01017-4
Chuanchen, D. U., ZHENG, Y., Qianqian, G. U. O., & Guoxiong, L. I. U. (2025) · Advances in Psychological Science · doi:10.3724/sp.j.1042.2025.2027
MoPHoney: An adaptive honeyword generation system based on Mixture-of-prompts
Chen, Y., Yang, X., Dong, F., Jiang, B., Lu, Z., & Liu, B. (2025) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2025.103617
Undead Signs: On the Possibility of a Computational Illusion of Meaning
Tritschler, M. (2025) · Philosophy & Technology · doi:10.1007/s13347-025-00995-1
Prosocial When Simple and Cold-Hearted When Complex: How Task Difficulty Shapes LLM Behavior
Kirshner, S. N., Pan, Y., & Wu, J. X. (2025) · Decision Analysis · doi:10.1287/deca.2025.0396
GPT’s emotion venting and punishment: the evolution from chaos to order
Wang, G., Li, J., Wang, W., Wang, Y., & Niu, X. (2025) · Humanities and Social Sciences Communications · doi:10.1057/s41599-025-06197-6
Thakur, A., Murray, T., Rodriguez, P., & Hilbert, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6083909
Synthetic Science from Large Language Models
Spaide, R. F. (2026) · Retina · doi:10.1097/iae.0000000000004805
Selitskiy, S., & Inoue, C. (2025) · International Conference on Foundation and Large Language Models (FLLM) · doi:10.1109/fllm67465.2025.11391110
Machine Eye: Designing Relational Engagement with Embodied Large Language Models
Ng, A., Rajcic, N., & Page, R. (2026) · International Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3793387 · Cited by 1 · see citing works
“Amazing, they all lean left” – analysing the political temperaments of current LLMs
Neuman, W. R., Coleman, C., Dasdan, A., Ali, S., Shah, M., & Meghani, K. (2026) · Journal of Psychology and AI · doi:10.1080/29974100.2026.2667948
Agostini, S. (2026) · trilogía Ciencia Tecnología Sociedad · doi:10.22430/21457778.3700
Which Individual Differences Predict Success at an LLM-integrated Search Task?*
Calbi, S. L. (2026) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3774935.3803066
Can Large Language Models Reason Strategically? Evidence From Attacker–Defender Signaling Games
Unal-Eyi, S., & Zhuang, J. (2026) · Risk Analysis · doi:10.1111/risa.70284
Deception in clinical large language models: an under-recognised safety risk
Reddy, A., Zhu, D. T., Khan, K., & Celi, L. A. (2026) · The Lancet Digital Health · doi:10.1016/j.landig.2026.101043
Investigating The Usefulness of Probes for Causal Intervention in Large Language Models
Maag, F., Woldai, B., Schacht, S., Guggenberger, M., & Heithoff, I. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-30860-3_9
Harmful Content Moderation in e-Participation Platforms
Vidal, R., Neto, M., Dias, T., Tomas, P. R., Rosa, L., & Cordeiro, L. (2026) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-30507-7_12
Rajput, A., Lavanya, S., Aleem, B. S., Menaka, S. R., Poornima, M. M., & Ayyappa Chakravarthi, N. (2026) · IGI Global eBooks · doi:10.4018/979-8-2600-0532-3.ch007
Should Care Robots Answer? Rethinking Moral Answerability Beyond Humans
Kropf, M. (2026) · Nursing Inquiry · doi:10.1111/nin.70150
Hila, A. A. (2026) · Philosophy & Technology · doi:10.1007/s13347-026-01168-4 · Cited by 1 · see citing works
Jaarsma, E. H., Ring, D., Wickman, J., & (24182938), A. D. (2026) · The Journal Of Hand Surgery · doi:10.1016/j.jhsa.2026.07.014
Fahy, C., McDonald, N., Keenan, K., & Corrigan, S. (2026) · AI Magazine · doi:10.1002/aaai.70073
The Mens Rea Evaluator: Can AI Tell Us When It's Biased?Preprint
Ghosh, R. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7446198
Wang, K., Pan, Z., & Lu, Y. (2026) · Computers in Human Behavior · doi:10.1016/j.chb.2026.109201
Gilbert, D. (2026) · Bulletin of the Council for Research in Music Education · doi:10.5406/21627223.250.1.03
Colloquial Parsing: Evaluating Deep Learning Approaches for Indonesian Fraud Detection
Halim, K. J., Murteja, T. A., Edbert, I. S., & Ndruru, S. (2026) · International Conference on ICT for Smart Society (ICISS) · doi:10.1109/iciss71466.2026.11715515
Greis, N. P., Rohde, W., & Doten, R. (2026) · Manufacturing Letters · doi:10.1016/j.mfglet.2026.08.038
- Authors
- Hagendorff, T.
- Affiliations
- University of Stuttgart (DE)
- Corresponding author
- Hagendorff, Thilo
- ORCID
- Hagendorff, Thilo
- Venue
- Proceedings of the National Academy of Sciences
- Publisher
- National Academy of Sciences
- Published
- 2024-06-04
- Volume
- 121
- Issue
- 24
- Pages
- e2317967121-e2317967121
- ISSN
- 0027-8424 (ISSN-L)
- 1091-6490
- PMC
- PMC11181111
- OpenAlex
- W4399320026
- Cited by
- 100
- References
- 58
- Citations by year
- 2026: 40 · 2025: 43 · 2024: 16 · 2023: 1
- FWCI
- 41.03
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Proceedings of the National Academy of Sciences (publishedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion, other-oa)
- OSF Preprints (OSF Preprints) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Ministry of Science, Research, and Arts Baden W&#x00FC;rttemberg (Az. 33-7533-9-19/54/5)
- Topics
- Social Sciences › Safety Research › Ethics and Social Impacts of AI
- Social Sciences › Psychology › Social Psychology › Deception detection and forensic psychology
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- large language models, deception, chain-of-thought reasoning, Machiavellianism, GPT-4, AI alignment
- MeSH terms
- Artificial Intelligence, Humans, Language, Deception
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
