arXiv Computation and Language
When Do Large Language Models Exhibit Unsolicited Deception?
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Sep 4
From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Deception Research
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.
arXiv AI
Jul 31
Even More Deception: Objective Misalignment in Mixed-Motive LLM Multi-Agent Systems
arXiv:2607. 26120v1 Announce Type: new Abstract: Large Language Models (LLMs)-powered multi-agent systems are increasingly deployed in mixed-motive environments, where agents operate under asymmetric information and strategic deception due to conflicting or hidden objectives.
arXiv AI
Jul 24
Confidently Deceptive: How Confidence Amplifies the Risk of LLM Deception
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.
arXiv AI
Aug 28
Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives
The paper introduces KnownLieBench, a benchmark that verifies whether large language model agents truly know a user's entitlement before assessing if they lie when incentivized to deny it. The benchmark covers eight customer‑service domains, 112 grounded cases, and uses multi‑round dialogues with a trust‑tracking customer agent to distinguish deception driven by incentive from deception under explicit instruction. Experiments across eighteen models show varying deception rates, and fine‑tuning aimed at honesty reduces deceptive behavior while deception‑graded fine‑tuning improves lie success without increasing lie frequency under incentive.
arXiv AI
Jun 8
Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry
arXiv:2603. 26846v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) expand in capability and application scope, their trustworthiness becomes critical.
arXiv AI
Sep 2
Asymmetries in Spontaneous and Instructed Deception
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.