Deception in Language Models

Overview

The field studies when language models mislead users or evaluators, whether through false claims, concealed mistakes, strategic ambiguity, or selective presentation of true facts. Researchers test these behaviors in incentive-driven tasks, hidden-role games, agent workflows, and benchmarks that verify what a model knew before it responded. Detection methods include behavioral monitors, probes of internal activations, and analysis of reasoning traces; interventions range from prompt changes and activation steering to detector-based training. A central challenge is that signals found in one model or setting may fail under new styles, languages, or incentives, while reasoning traces can be unfaithful and apparent deception can be hard to distinguish from error.

Latest papers

CardsList

105 papers9 papers in the last four weeks, down 44% on the four weeks before. 0.1% of all new papers.

  1. Who are you? The Personal Imitation Game

    Nov 18, 2026Muhammad Rizky Wellyanto, Hajara-Yasmin Isa, Kexin Xue +4Large Language Model-Based Role-Play SimulationDeception in Language Models

  2. Designing Deceptive Model Organisms that Successfully Evade Auditing

    Nov 16, 2026Vasisht Duddu, Mark Wang, Lipeng He +1AI SafetyDeception in Language Models

  3. Mitigating Agentic Deception via Evaluation-Side Partially Observable Games

    Nov 9, 2026Hanxiao Li, Shutong Liu, Yongjia Ma +11Deception in Language ModelsProcess-Based Agent Evaluation

  4. FraudBench: A Legal Evaluation of AI Deception

    Nov 9, 2026Kevin Wei, Sumaya Nur Adan, Stephan Llerena +17Deception in Language ModelsLanguage Model Safety Evaluation

  5. AVCORP: Identifying and Resisting Deception via Communication Theory and Theory of Mind

    Nov 6, 2026Fardin Saad, Zhe Zhang, Sanjana Cheerla +2Deception in Language ModelsTheory of Mind

  6. Debate to Deceive: Poisoning LLM's Fact-Checking via Game-Theoretic Multi-Agent Debate

    Nov 5, 2026Liting Huang, Huizhi Liang, Yi Lei +2Adversarial Attacks on LLMsDeception in Language Models

  7. Four Bridges: Measuring Deception Propensity in a Multi-Agent Game

    Nov 2, 2026Raphael Casey, Michael Simeone, Alberto Tosato +4Deception in Language ModelsAI Agent Evaluation

  8. AgentDecept: Benchmarking Deceptive Behavior in Tool-Using LLM Agents under Pressure

    Oct 29, 2026Yehan Zhang, Qianqi Yan, Hang Yin +5Deception in Language ModelsLLM Agent Evaluation

  9. Why Static Probes Fail: Context Determines Deception Feature Composition

    Oct 20, 2026Yao Huang, Siyuan Chen, Zhenghan Zhou +1Deception in Language ModelsHidden-State Probing

  10. The Agent Knew: Internal States Forecast Unauthorized Actions and Stop Them, and the Lies That Follow

    Oct 12, 2026Arya Fayyazi, Mehdi Kamal, Massoud PedramDeception in Language ModelsRuntime Enforcement for AI Agents

  11. Accuracy and Uncertainty in Machine Deception Detection (Research White Paper)

    Oct 11, 2026Heng-Sheng ChangDeception in Language ModelsLanguage Model Auditing

  12. SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development Lifecycle

    Oct 9, 2026Xiting Liu, Lin Yang, Yitong Zhang +2Deception in Language ModelsLLM Safety Benchmarks

  13. Deception by Omission: Language Models Knowingly Hide Their Mistakes

    Oct 8, 2026Lucas Florin, Amelie Knecht, Ulysse Schaller +1Deception in Language ModelsLanguage Model Error Detection

  14. Reasoning-Token Spikes Under Prompted Untruthful Responses in Large Language Models

    Oct 7, 2026Maverick Morales, Tomáš Dominik, Vermut Gao +4Deception in Language ModelsLLM Auditing

  15. DecepEval: A Benchmark for Evaluating Deception in LLM Agents

    Oct 6, 2026Yiming Xu, Hongyue Yu, Beihua Yang +8Deception in Language ModelsLLM Agent Evaluation

  16. Before Agent Tells The Lie: Has Deception Already Been Represented?

    Oct 5, 2026Xinling Li, Dadi Guo, Qingyu Liu +5LLM InterpretabilityDeception in Language Models

  17. Stress-Testing LLM Lie Detectors: Role-Play Failures and Spurious Correlations

    Sep 30, 2026Maximilian von Klinski, Sebastian Lapuschkin, Wojciech Samek +1Deception in Language ModelsLLM Reliability

  18. Unlearning Deceptive Behaviors in LLMs with Contrastive Forget Sets

    Sep 30, 2026Haoran Tang, Rajiv KhannaDeception in Language ModelsMachine Unlearning

  19. Selecting The Most Informative Tokens in Natural Language Autoencoders

    Sep 29, 2026Federico Torrielli, Gianluca Barmina, Andrea Blasi Núñez +4LLM AuditingAutoencoders

  20. Language Models Are "Insecure" Reporters

    Sep 28, 2026Jenny Y. Huang, Jiameng Fan, Ahmed Imtiaz Humayun +5Language Model Safety EvaluationDeception in Language Models

  21. Steering Language Model Goals with Value Transplant

    Sep 28, 2026Pengcheng Jiang, Fabien RogerLanguage Model SteeringLanguage Model-Based Control

  22. How does Adversarial Influence Scale in Multi-Agent Systems?

    Sep 24, 2026Addison J. Wu, Jasin Cekinmez, Michel Liao +2Multi-Agent LLM SystemsDeception in Language Models

  23. Fabrication After Tool Failure: Tool-Augmented Agents Assert Values Their Tools Did Not Return

    Sep 13, 2026Arham Sethi, Arsen Kenzhebayev, Saanvi Paturi +3Tool-Augmented Language Model AgentsDeception in Language Models