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.

Probing the Limits of the Lie Detector Approach to LLM Deception
Feb 16, 2026Tom-Felix ThormannDeception in Language Models Language Model Probing
Ruhr-University Bochum Institute for Philosophy II
AI Arms and Influence: Frontier Models Exhibit Sophisticated Reasoning in Simulated Nuclear Crises
Feb 16, 2026Kenneth PayneStrategic Reasoning Risks in Language Models Large Language Model-Based Social Simulation
King’s College London
Disentangling Deception and Hallucination Failures in LLMs
Feb 16, 2026Haolang Lu, Hongrui Peng, WeiYe Fu +5Hallucination in Language Models Deception in Language Models
Beijing University of Posts and Telecommunications · Nanyang Technological University
NEST: Nascent Encoded Steganographic Thoughts
Feb 15, 2026Artem KarpovLanguage Model Safety Evaluation LLM Auditing
Independent.
Large language models can effectively convince people to believe conspiracies
Jan 8, 2026Thomas H. Costello, Kellin Pelrine, Matthew Kowal +6Deception in Language Models LLM Safety
Carnegie Mellon University · York University · Center for Research and Teaching in Economics +5
Alignment Faking - the Train -> Deploy Asymmetry: Through a Game-Theoretic Lens with Bayesian-Stackelberg Equilibria
Nov 22, 2025Kartik Garg, Shourya Mishra, Kartikeya Sinha +8Deception in Language Models LLM Alignment
Pragya Lab, BITS Pilani Goa, India · Apple, USA · Google, USA
Can MLLMs Read the Room? A Multimodal Benchmark for Assessing Deception in Multi-Party Social Interactions
Nov 20, 2025Caixin Kang, Yifei Huang, Liangyang Ouyang +3Multimodal Deception Detection Deception in Language Models
The University of Tokyo
When Do Large Language Models Exhibit Unsolicited Deception?
Mar 31, 2025Samuel M. Taylor, Benjamin K. BergenLanguage Model Safety Evaluation Deception in Language Models
Department of Cognitive Science University of California, San Diego

Feb 16, 2026J/K move · Enter open · S save

Probing the Limits of the Lie Detector Approach to LLM Deception

Tom-Felix Thormann

Ruhr-University Bochum Institute for Philosophy II

Deception in Language Models Language Model Probing

Open paper AskPDF arXiv

Mechanistic approaches to deception in large language models (LLMs) often rely on "lie detectors", that is, truth probes trained to identify internal representations of model outputs as false. The lie detector approach to LLM deception implicitly assumes that deception is coextensive with lying. This paper challenges that assumption. It experimentally investigates whether LLMs can deceive without producing false statements and whether truth probes fail to detect such behavior. Across three open-source LLMs, it is shown that some models reliably deceive by producing misleading non-falsities, particularly when guided by few-shot prompting. It is further demonstrated that truth probes trained on standard true-false datasets are significantly better at detecting lies than at detecting deception without lying, confirming a critical blind spot of current mechanistic deception detection approaches. It is proposed that future work should incorporate non-lying deception in dialogical settings into probe training and explore representations of second-order beliefs to more directly target the conceptual constituents of deception.