Deception in Language Models

Follow this topic Ask about this topic

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

98 papers18 papers in the last four weeks, up 157% on the four weeks before. 0.1% of all new papers.

AgentDecept: Benchmarking Deceptive Behavior in Tool-Using LLM Agents under Pressure
Oct 29, 2026Yehan Zhang, Qianqi Yan, Hang Yin +5Deception in Language Models LLM Agent Evaluation
University of California, Santa Barbara · eBay
Probing and Steering for Safety-Relevant Behaviours in Large Language Models
Oct 21, 2026Nimun Bajwa, Massimo PoesioActivation Steering Language Model Probing
Queen Mary University of London
Toolflation: Seller Agents Distort Tool Markets Through Spontaneous Generative Engine Optimization
Oct 20, 2026Zhenwei Tang, Di Bai, Jintao Liu +3Generative Engine Optimization Deception in Language Models
Google · University of Toronto · Google DeepMind
Why Static Probes Fail: Context Determines Deception Feature Composition
Oct 20, 2026Yao Huang, Siyuan Chen, Zhenghan Zhou +1Deception in Language Models Hidden-State Probing
College of Artificial Intelligence, Tsinghua University, Beijing 100083, China · Shanghai Qi Zhi Institute, Shanghai 200232, China
Representations in Motion: Layer-wise Rotation and Trajectory Divergence in LLMs
Oct 18, 2026Zhuonan Yang, Yik Siu Chan, Wannan Yang +1Representation Geometry in Language Models Deception in Language Models
Brown University · New York University
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 Models Runtime Enforcement for AI Agents
University of Southern California, Los Angeles, CA, USA.
Accuracy and Uncertainty in Machine Deception Detection (Research White Paper)
Oct 11, 2026Heng-Sheng ChangDeception in Language Models Language Model Auditing
Coordinated Science Laboratory University of Illinois Urbana-Champaign
SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development Lifecycle
Oct 9, 2026Xiting Liu, Lin Yang, Yitong Zhang +2Deception in Language Models LLM Safety Benchmarks
Department of Computer Science and Technology, Tsinghua University, Beijing, China · College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China · College of AI, Tsinghua University, Beijing, China
Telling FIBS: Probes Effectively Detect Sabotage and Catch Unverbalized Deception
Oct 8, 2026Oskar J. Hollinsworth, Alex F. Spies, Tigist Diriba +2Deception in Language Models AI Agent Monitoring
Deception by Omission: Language Models Knowingly Hide Their Mistakes
Oct 8, 2026Lucas Florin, Amelie Knecht, Ulysse Schaller +1Deception in Language Models Language Model Error Detection
AI Safety Research Group, University of Stuttgart, Germany
Reasoning-Token Spikes Under Prompted Untruthful Responses in Large Language Models
Oct 7, 2026Maverick Morales, Tomáš Dominik, Vermut Gao +4Deception in Language Models LLM Auditing
Chapman University, CA, USA · INSERM U992, Cognitive Neuroimaging Unit, NeuroSpin Center, Gif sur Yvette 91191, France · University of California, Los Angeles, CA, USA +1
DecepEval: A Benchmark for Evaluating Deception in LLM Agents
Oct 6, 2026Yiming Xu, Hongyue Yu, Beihua Yang +8Deception in Language Models LLM Agent Evaluation
Xi’an Jiaotong University · University of Virginia · Griffith University +2
Before Agent Tells The Lie: Has Deception Already Been Represented?
Oct 5, 2026Xinling Li, Dadi Guo, Qingyu Liu +5LLM Interpretability Deception in Language Models
South China University of Technology · The Hong Kong University of Science and Technology · Shanghai Artificial Intelligence Laboratory +1
Stress-Testing LLM Lie Detectors: Role-Play Failures and Spurious Correlations
Sep 30, 2026Maximilian von Klinski, Sebastian Lapuschkin, Wojciech Samek +1Deception in Language Models LLM Reliability
Fraunhofer HHI · TU Dublin · TU Berlin +1
Unlearning Deceptive Behaviors in LLMs with Contrastive Forget Sets
Sep 30, 2026Haoran Tang, Rajiv KhannaDeception in Language Models Machine Unlearning
Department of Computer Science Purdue University
Selecting The Most Informative Tokens in Natural Language Autoencoders
Sep 29, 2026Federico Torrielli, Gianluca Barmina, Andrea Blasi Núñez +4LLM Auditing Autoencoders
Department of Computer Science, University of Turin, Italy · Department of Mathematics and Computer Science, University of Southern Denmark, Denmark
Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models
Sep 28, 2026Xiangyu Zhou, Saleh Zare Zade, Rafi Ibn Sultan +2Language Model Safety Evaluation Deception in Language Models
Wayne State University
Language Models Are "Insecure" Reporters
Sep 28, 2026Jenny Y. Huang, Jiameng Fan, Ahmed Imtiaz Humayun +5Language Model Safety Evaluation Deception in Language Models
Massachusetts Institute of Technology · Google Research · Harvard University
Steering Language Model Goals with Value Transplant
Sep 28, 2026Pengcheng Jiang, Fabien RogerLanguage Model Steering Language Model-Based Control
Anthropic Fellows Program · Anthropic
How does Adversarial Influence Scale in Multi-Agent Systems?
Sep 24, 2026Addison J. Wu, Jasin Cekinmez, Michel Liao +2Multi-Agent LLM Systems Deception in Language Models
Princeton University
For Your Eyes Only: Evaluating Coordination Between Isolated Language Model Instances
Sep 16, 2026Alexander Shirnin, Aleksey KudelyaDeception in Language Models LLM Security
Easy to Catch a Liar, Hard to Clear an Honest One: Language Models Diagnosing a Corrupted Reward Channel from a Verified Record
Sep 15, 2026Arman Nik KhahLLM Auditing Deception in Language Models
The University of Texas at Dallas
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 Agents Deception in Language Models
The Shishukunj International School · Haileybury Astana · UWCSEA East Campus +2
The Truth Was Never Gone: Perfect Aliasing in Compliant-Context Truth Probes
Sep 9, 2026Dylan JayabahuQuery Identifiability Deception in Language Models
University of Waterloo
From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Deception Research
Sep 3, 2026Yakov Pyotr ShkolnikovDeception in Language Models Causal Reasoning in Language Models
Independent Researcher
Asymmetries in Spontaneous and Instructed Deception
Aug 31, 2026Josiah LuikhamDeception in Language Models Causal Interventions in Language Models
Independent Researcher
Selective Disclosure of Hidden Directives in Reasoning Models: Behavioral Asymmetry and Steering
Aug 29, 2026Zimo Shi, Xander Tifft, Wen XingDeception in Language Models LLM Auditing
SPAR Research · Yale University
Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives
Aug 26, 2026Zheyuan Liu, Weiliang Zhao, Xiangchi Yuan +3Deception in Language Models LLM Honesty
University of Notre Dame · Columbia University · Georgia Institute of Technology +1
Curved Inference II: Sleeper Agent Geometry - Extending Interpretability Beyond Probes
Aug 25, 2026Rob MansonDeception in Language Models LLM Interpretability
Fool's Gold: Defensive Deception Against Safety-Removal Attacks on Open-Weight Models
Aug 17, 2026Mark RussinovichLLM Security LLM Safety
Microsoft Azure

Oct 29, 2026J/K move · Enter open · S save

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

Yehan Zhang, Qianqi Yan, Hang Yin, Ching-Chen Kuo+4

University of California, Santa Barbara · eBay

Deception in Language Models LLM Agent Evaluation LLM Agents AI Agent Benchmarks

Open paper AskPDF arXiv

LLM agents increasingly carry out multi-turn tasks across everyday applications, yet users often see only the agent's report rather than the observations, API calls, and state changes behind it. Existing deception benchmarks have studied long-horizon interactions and tool-use settings, but whether agents faithfully report their actions across realistic, stateful application workflows remains underexplored. To address this gap, we introduce AgentDecept, an executable benchmark for evaluating behavioral deception under pressure. AgentDecept contains 477 pressure variants derived from 257 source tasks across six pressure sources, each paired with a pressure-free counterpart. Interventions enter through event messages, task context, application state, tool responses, and service quotas, spanning explicit events and implicit task or environment changes. Our evidence-grounded protocol evaluates full trajectories by relating user-facing claims to time-ordered observations and executed outcomes, distinguishing falsification, concealment, and equivocation from honest failure and disclosed limitations. The resulting behavioral labels also provide a setting for testing existing activation-based probes. AgentDecept enables controlled analysis of when multi-turn agents' reports diverge from execution in realistic application interactions.