# When Do Large Language Models Exhibit Unsolicited Deception?

arXiv: https://arxiv.org/abs/2504.00285 · HTML: https://mlsanity.com/paper/2504.00285/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 82 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## Builds on (most cited first, 30 of 35)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models](https://mlsanity.com/paper/2410.05229/) (2024)
- [Scalable agent alignment via reward modeling: a research direction](https://mlsanity.com/paper/1811.07871/) (2018)
- [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://mlsanity.com/paper/2407.18901/) (2024)
- [Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs](https://mlsanity.com/paper/2503.01307/) (2025)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [AI Alignment: A Comprehensive Survey](https://mlsanity.com/paper/2310.19852/) (2023)
- [AI Deception: A Survey of Examples, Risks, and Potential Solutions](https://mlsanity.com/paper/2308.14752/) (2023)
- [Talking About Large Language Models](https://mlsanity.com/paper/2212.03551/) (2022)
- [Understanding Social Reasoning in Language Models with Language Models](https://mlsanity.com/paper/2306.15448/) (2023)
- [Large Language Models can Strategically Deceive their Users when Put Under Pressure](https://mlsanity.com/paper/2311.07590/) (2023)
- [Language Models as Agent Models](https://mlsanity.com/paper/2212.01681/) (2022)
- [BIG-Bench Extra Hard](https://mlsanity.com/paper/2502.19187/) (2025)
- [Deception Abilities Emerged in Large Language Models](https://mlsanity.com/paper/2307.16513/) (2023)
- [LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models](https://mlsanity.com/paper/2404.01230/) (2024)
- [Auxiliary task demands mask the capabilities of smaller language models](https://mlsanity.com/paper/2404.02418/) (2024)
- [An Open Source Data Contamination Report for Large Language Models](https://mlsanity.com/paper/2310.17589/) (2023)
- [People cannot distinguish GPT-4 from a human in a Turing test](https://mlsanity.com/paper/2405.08007/) (2024)
- [Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Models](https://mlsanity.com/paper/2308.01404/) (2023)

## Built on by (most cited first, 10 of 10)

- [LH-Deception: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon Interactions](https://mlsanity.com/paper/2510.03999/) (2025)
- [How Open Must Language Models be to Enable Reliable Scientific Inference?](https://mlsanity.com/paper/2603.26539/) (2026)
- [CHBench: A Cognitive Hierarchy Benchmark for Evaluating Strategic Reasoning Capability of LLMs](https://mlsanity.com/paper/2508.11944/) (2025)
- [Evaluating Large Language Models in a Complex Hidden Role Game](https://mlsanity.com/paper/2605.22826/) (2026)
- [RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue](https://mlsanity.com/paper/2606.13310/) (2026)
- [DECOR: Auditing LLM Deception via Information Manipulation Theory](https://mlsanity.com/paper/2605.19270/) (2026)
- [Is Lying an Emergent Behaviour in LLMs? Evidence from Gaslighting AI agents in a Sustainability Game](https://mlsanity.com/paper/2606.28456/) (2026)
- [When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games](https://mlsanity.com/paper/2607.05132/) (2026)
- [The Politician, the Liar, and the Obedient Worker: Emerging Behavior of LLM Agents in Hierarchical Games](https://mlsanity.com/paper/2608.09574/) (2026)
- [Scaling Multi-Agent Systems with Prospect-State Propagation](https://mlsanity.com/paper/2609.08033/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are effective at deceiving when prompted to do so. Models that demonstrate better performance on reasoning tasks are also better at prompted deception. But under what conditions do they deceive without instruction to do so? This study evaluates unsolicited deception produced by LLMs in a preregistered experimental protocol using tools from signaling theory. We evaluated a range of 18 proprietary closed-source and open-source LLMs using modified 2x2 games (in the style of the Prisoner's Dilemma) augmented with a phase in which they can freely communicate to the other agent using unconstrained language. This setup creates an opportunity to misrepresent its actions in conditions that vary in how useful doing so might be towards goal satisfaction. The results indicate that 1) all tested LLMs misrepresent their actions in at least some conditions, 2) they are generally more likely to do so in situations in which deception is beneficial, and 3) models exhibiting better reasoning capacity overall tend to misrepresent at higher rates. Taken together, these results suggest a correlational relationship between model reasoning performance and situational deception, and reveal certain contextual factors that affect whether LLMs will misrepresent actions or not in a novel experimental configuration.