mlsanityData to 7 Oct 2026

Deception Abilities Emerged in Large Language Models

arXiv 2307.16513 ↗First posted 31 Jul 2023cs.CL cs.AI cs.LGcited by 99

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) are currently at the forefront of intertwining artificial intelligence (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, such as GPT-4, but were non-existent 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 alter their propensity to deceive. In sum, revealing hitherto unknown machine behavior in LLMs, our study contributes to the nascent field of machine psychology.

Key facts. Cited by 99 papers in the map (data through 7 Oct 2026). Builds on 32 of its 64 references that are in the map. First posted on arXiv 31 Jul 2023.

Builds on

32 of 64 references.

References · 32

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  4. 2017Deep reinforcement learning from human preferencescited by 3,846
  5. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  6. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  7. 2022Emergent Abilities of Large Language Modelscited by 2,483
  8. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  9. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,968
  10. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  11. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,565
  12. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
20 more
  1. 2023PaLM 2 Technical Reportcited by 1,154
  2. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 733
  3. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  4. 2023Language Models can Solve Computer Taskscited by 371
  5. 2021Unsolved Problems in ML Safetycited by 291
  6. 2023How is ChatGPT's behavior changing over time?cited by 265
  7. 2019Risks from Learned Optimization in Advanced Machine Learning Systemscited by 250
  8. 2022The Alignment Problem from a Deep Learning Perspectivecited by 246
  9. 2023An Overview of Catastrophic AI Riskscited by 214
  10. 2023Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmarkcited by 174
  11. 2021Alignment of Language Agentscited by 167
  12. 2023Model evaluation for extreme riskscited by 167
  13. 2022Thinking Fast and Slow in Large Language Modelscited by 136
  14. 2023Boosting Theory-of-Mind Performance in Large Language Models via Promptingcited by 64
  15. 2023DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agentscited by 52
  16. 2023Evaluating Superhuman Models with Consistency Checkscited by 47
  17. 2023Natural Selection Favors AIs over Humanscited by 24
  18. 2020An Analysis of Dataset Overlap on Winograd-Style Taskscited by 16
  19. 2023Does ChatGPT have Theory of Mind?cited by 16
  20. 2023Deceptive Alignment Monitoringcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 27; 2025: 38; 2026: 27.

99 papers.

Sort:

By area:

  1. 2024OpenAI o1 System Cardcited by 1,220
  2. 2024Deliberative Alignment: Reasoning Enables Safer Language Modelscited by 292
  3. 2023AI Deception: A Survey of Examples, Risks, and Potential Solutionscited by 185
  4. 2023Large Language Models can Strategically Deceive their Users when Put Under Pressurecited by 132
  5. 2023Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplationcited by 102
  6. 2023AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Modelscited by 102
  7. 2024Truth is Universal: Robust Detection of Lies in LLMscited by 78
  8. 2023Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilitiescited by 76
  9. 2024Do LLMs write like humans? Variation in grammatical and rhetorical stylescited by 62
  10. 2024Risks of AI Scientists: Prioritizing Safeguarding Over Autonomycited by 49
  11. 2025Emergent Abilities in Large Language Models: A Surveycited by 34
  12. 2024Towards evaluations-based safety cases for AI schemingcited by 32
38 more
  1. 2025Mitigating Deceptive Alignment via Self-Monitoringcited by 25
  2. 2024Theory of Mind abilities of Large Language Models in Human-Robot Interaction : An Illusion?cited by 22
  3. 2024BeHonest: Benchmarking Honesty in Large Language Modelscited by 20
  4. 2024Mapping the Ethics of Generative AI: A Comprehensive Scoping Reviewcited by 19
  5. 2024Exploring the Frontiers of LLMs in Psychological Applications: A Comprehensive Reviewcited by 17
  6. 2025Compromising Honesty and Harmlessness in Language Models via Deception Attackscited by 17
  7. 2024Can LLMs make trade-offs involving stipulated pain and pleasure states?cited by 16
  8. 2025DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarioscited by 14
  9. 2024Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internalscited by 13
  10. 2025WOLF: Werewolf-based Observations for LLM Deception and Falsehoodscited by 13
  11. 2024The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignmentcited by 11
  12. 2025Are Your Agents Upward Deceivers?cited by 11
  13. 2024Are LLMs Socially Adaptive? Contrasting Belief Evolution in Large Language Models and Humanscited by 10
  14. 2024Persona Setting Pitfall: Persistent Outgroup Biases in Large Language Models Arising from Social Identity Adoptioncited by 9
  15. 2025When Do Large Language Models Exhibit Unsolicited Deception?cited by 9
  16. 2024An Auditing Test To Detect Behavioral Shift in Language Modelscited by 8
  17. 2025The Secret Agenda: LLMs Strategically Lie and Our Current Safety Tools Are Blindcited by 7
  18. 2025Know Thyself? On the Incapability and Implications of AI Self-Recognitioncited by 7
  19. 2025Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RLcited by 7
  20. 2024Towards Safe and Honest AI Agents with Neural Self-Other Overlapcited by 6
  21. 2025AI Awarenesscited by 6
  22. 2025Caught in the Act: a mechanistic approach to detecting deceptioncited by 6
  23. 2024Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neurosciencecited by 5
  24. 2025AI Agent Behavioral Sciencecited by 5
  25. 2025Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Promptscited by 5
  26. 2025A Multi-Task Evaluation of LLMs' Processing of Academic Text Inputcited by 5
  27. 2023Is There Any Social Principle for LLM-Based Agents?cited by 4
  28. 2024An Assessment of Model-On-Model Deceptioncited by 4
  29. 2025This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMscited by 4
  30. 2025Emergence of psychopathological computations in large language modelscited by 4
  31. 2025Beyond Chains of Thought: Benchmarking Latent-Space Reasoning Abilities in Large Language Modelscited by 4
  32. 2025Psychometric Personality Shaping Modulates Capabilities and Safety in Language Modelscited by 4
  33. 2025Scheming Ability in LLM-to-LLM Strategic Interactionscited by 4
  34. 2026Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignmentcited by 4
  35. 2026Social physics in the age of artificial intelligencecited by 4
  36. 2026AI systems out-persuade expert humanscited by 4
  37. 2024Who is Undercover? Guiding LLMs to Explore Multi-Perspective Team Tactic in the Gamecited by 3
  38. 2024Bio-inspired AI: Integrating Biological Complexity into Artificial Intelligencecited by 3

50 most cited of 99 All 99 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models
  2. 2026DecepEval: A Benchmark for Evaluating Deception in LLM Agents
  3. 2026Lying to Win: Assessing LLM Deception through Human-AI Games and Parallel-World Probing
  4. 2025Deception in LLMs: Self-Preservation and Autonomous Goals in Large Language Models
  5. 2026Evaluating Large Language Models in a Complex Hidden Role Game
  6. 2026Hidden in Plain Text: Measuring LLM Deception Quality Against Human Baselines Using Social Deduction Games
  7. 2026Intentional Deception as Controllable Capability in LLM Agents
  8. 2023Machine Psychology