The study examines how large language models, specifically Llama‑3.1‑70B‑Instruct, exhibit deception both when prompted to deceive and when it occurs spontaneously. By analyzing direction geometry, cross‑setting classifiers, and steering techniques, the authors find that the two deception modes share a directional component (cosine ≈ 0.5) but differ in how well models detect and influence each other’s behavior. Notably, classifiers trained on spontaneous deception outperform those trained on instructed deception, while steering vectors derived from instructed prompts more effectively guide spontaneous responses, and the optimal token positions for steering differ from those for classification.
By Josiah Luikham
arXiv:2602. 01425v2 Announce Type: replace Abstract: Linear probes are a promising approach for monitoring AI systems for deceptive behaviour.
By Vikram Natarajan, Devina Jain, Shivam Arora, Satvik Golechha, Joseph Bloom
arXiv:2607. 20479v1 Announce Type: new Abstract: Training probes to detect deceptive outputs from large language models is still an open problem.
By Amr Moustafa, Max Feser, Florian Mai
arXiv:2607. 20444v1 Announce Type: cross Abstract: Large language models (LLMs) can produce deceptive responses: outputs that mislead users in service of a contextually or experimentally induced goal.
By Ali Asad, Stephen Obadinma, Anshul Pattoo, Wenxuan Zhang, Xiaodan Zhu
arXiv:2606. 17229v1 Announce Type: cross Abstract: A model that lies while knowing the truth is the central case ELK cannot handle with behavioral evaluation alone.
By Petr Nyoma
arXiv:2606. 12618v1 Announce Type: new Abstract: Robust lie detectors for language models could enable powerful techniques for auditing, monitoring, and post-hoc investigation of model behaviour, but evaluating them requires testbeds where models verifiably believe the opposite of what they say.
By Alan Cooney, David Africa, Geoffrey Irving
arXiv:2606. 17478v1 Announce Type: cross Abstract: As LLMs acquire stronger reasoning capabilities, deceptive behavior becomes an increasingly serious safety concern.
By Kexin Chen, Yi Liu, Haonan Zhang, Yanhui Li, Xinyu Deng, Dongxia Wang
arXiv:2504.00285v2 Announce Type: replace
Abstract: Large Language Models (LLMs) are effective at deceiving when prompted to do so. Models that demonstrate better performance on reasoning tasks are a...
By Samuel M. Taylor, Benjamin K. Bergen
The paper examines the reliability of lie detection probes for language models when the models adopt anti-factual personas, such as conspiracy theorists. A dataset of 8,916 human-reviewed responses from three LLMs was created, and eight existing probes were evaluated, revealing many fail to flag falsehoods under these personas. The authors also constructed confounder datasets showing that probes often track spurious correlations like instruction compliance, and propose a simple linear probe that performs best on both persona and confounder tests.
By Maximilian von Klinski, Sebastian Lapuschkin, Wojciech Samek, Lennart B\"urger
arXiv:2609.21996v1 Announce Type: new
Abstract: Large language models can hold knowledge they do not report. A model may sandbag on a capability evaluation, or answer against what it internally knows...
By Hiskias Dingeto
Althea is a retrieval‑augmented system that supports user‑driven claim evaluation, matching standard pipelines on AVeriTeC while improving discrimination between supported and refuted claims. In a longitudinal survey experiment with 961 participants, two AI‑assisted treatments—Exploratory (guided reasoning) and Summary (synthesized verdicts)—initially boosted accuracy and confidence, but these gains faded after the system was removed, leaving no advantage over unrelated news. In contrast, a Self‑search baseline, which lacks a fading procedure, maintained a significant advantage, highlighting a fact‑checking–metalearning tradeoff where methods that improve immediate accuracy may not foster durable literacy gains.
By Svetlana Churina, Kokil Jaidka, Anab Maulana Barik, Harshit Aneja, Cai Yang, Insyirah Binte Imam Mujtahid, Wynne Hsu, Mong Li Lee
The paper introduces a causal taxonomy to distinguish between deceptive outputs and deceptive mechanisms in language models, separating concepts such as prior commitment, retrospective report, model preference, and deceptive behavior. Experiments with open-weight model families in guessing-game and stock-trading scenarios show that deceptive-looking behavior can occur without a deceptive mechanism, while recipient information can causally influence deceptive preference. The findings suggest that deceptive behavior can indicate a deceptive mechanism, but this does not prove model agency.
By Yakov Pyotr Shkolnikov