# Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Models

arXiv: https://arxiv.org/abs/2308.01404 · HTML: https://mlsanity.com/paper/2308.01404/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 24 references that are in the map.
- First posted on arXiv 5 Jul 2023.

## Builds on (most cited first, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [TextWorld: A Learning Environment for Text-based Games](https://mlsanity.com/paper/1806.11532/) (2018)
- [Inverse Scaling: When Bigger Isn't Better](https://mlsanity.com/paper/2306.09479/) (2023)
- [Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark](https://mlsanity.com/paper/2304.03279/) (2023)
- [Model evaluation for extreme risks](https://mlsanity.com/paper/2305.15324/) (2023)
- [Interactive Fiction Games: A Colossal Adventure](https://mlsanity.com/paper/1909.05398/) (2019)
- [Open Problems in Cooperative AI](https://mlsanity.com/paper/2012.08630/) (2020)
- [Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures](https://mlsanity.com/paper/2112.05224/) (2021)
- [What Would Jiminy Cricket Do? Towards Agents That Behave Morally](https://mlsanity.com/paper/2110.13136/) (2021)
- [Spear Phishing With Large Language Models](https://mlsanity.com/paper/2305.06972/) (2023)
- [Can large language models democratize access to dual-use biotechnology?](https://mlsanity.com/paper/2306.03809/) (2023)
- [Putting the Con in Context: Identifying Deceptive Actors in the Game of Mafia](https://mlsanity.com/paper/2207.02253/) (2022)
- [Hidden Agenda: a Social Deduction Game with Diverse Learned Equilibria](https://mlsanity.com/paper/2201.01816/) (2022)

## Built on by (most cited first, 30 of 47)

- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [AI Deception: A Survey of Examples, Risks, and Potential Solutions](https://mlsanity.com/paper/2308.14752/) (2023)
- [Large Language Models can Strategically Deceive their Users when Put Under Pressure](https://mlsanity.com/paper/2311.07590/) (2023)
- [AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways](https://mlsanity.com/paper/2406.02630/) (2024)
- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations](https://mlsanity.com/paper/2402.12348/) (2024)
- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation](https://mlsanity.com/paper/2310.01320/) (2023)
- [LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models](https://mlsanity.com/paper/2404.01230/) (2024)
- [How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions](https://mlsanity.com/paper/2309.15840/) (2023)
- [Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena](https://mlsanity.com/paper/2310.05746/) (2023)
- [How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments](https://mlsanity.com/paper/2403.11807/) (2024)
- [Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant](https://mlsanity.com/paper/2405.01576/) (2024)
- [InterIntent: Investigating Social Intelligence of LLMs via Intention Understanding in an Interactive Game Context](https://mlsanity.com/paper/2406.12203/) (2024)
- [Among Us: A Sandbox for Measuring and Detecting Agentic Deception](https://mlsanity.com/paper/2504.04072/) (2025)
- [Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models](https://mlsanity.com/paper/2412.01784/) (2024)
- [AgentLens: Visual Analysis for Agent Behaviors in LLM-based Autonomous Systems](https://mlsanity.com/paper/2402.08995/) (2024)
- [PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach](https://mlsanity.com/paper/2511.20703/) (2025)
- [Deception in LLMs: Self-Preservation and Autonomous Goals in Large Language Models](https://mlsanity.com/paper/2501.16513/) (2025)
- [Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models](https://mlsanity.com/paper/2412.17128/) (2024)
- [Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals](https://mlsanity.com/paper/2405.05466/) (2024)
- [WOLF: Werewolf-based Observations for LLM Deception and Falsehoods](https://mlsanity.com/paper/2512.09187/) (2025)
- [Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in Legislation](https://mlsanity.com/paper/2405.04325/) (2024)
- [When Do Large Language Models Exhibit Unsolicited Deception?](https://mlsanity.com/paper/2504.00285/) (2025)
- [Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL](https://mlsanity.com/paper/2510.14318/) (2025)
- [Among Them: A game-based framework for assessing persuasion capabilities of LLMs](https://mlsanity.com/paper/2502.20426/) (2025)
- [The Secret Agenda: LLMs Strategically Lie and Our Current Safety Tools Are Blind](https://mlsanity.com/paper/2509.20393/) (2025)
- [EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents](https://mlsanity.com/paper/2412.13549/) (2024)
- [AI Agent Behavioral Science](https://mlsanity.com/paper/2506.06366/) (2025)

## Abstract (arXiv)

Are current language models capable of deception and lie detection? We study this question by introducing a text-based game called textitHoodwinked, inspired by Mafia and Among Us. Players are locked in a house and must find a key to escape, but one player is tasked with killing the others. Each time a murder is committed, the surviving players have a natural language discussion then vote to banish one player from the game. We conduct experiments with agents controlled by GPT-3, GPT-3.5, and GPT-4 and find evidence of deception and lie detection capabilities. The killer often denies their crime and accuses others, leading to measurable effects on voting outcomes. More advanced models are more effective killers, outperforming smaller models in 18 of 24 pairwise comparisons. Secondary metrics provide evidence that this improvement is not mediated by different actions, but rather by stronger persuasive skills during discussions. To evaluate the ability of AI agents to deceive humans, we make this game publicly available at h https://hoodwinked.ai/ .