arXiv Computation and Language

When Do Large Language Models Exhibit Unsolicited Deception?

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.

By Yakov Pyotr Shkolnikov
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.

By Zheyuan Liu, Weiliang Zhao, Xiangchi Yuan, Ningshan Ma, Yue Huang, Meng Jiang
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.

By Josiah Luikham
arXiv AI
6d ago

Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions

The paper investigates why large language models (LLMs) struggle in strategic decision-making under incomplete information. It identifies two key gaps: an observation‑belief gap where LLMs’ internal representations of game states are accurate but brittle, and a belief‑action gap where converting these internal beliefs into actions is weak, leading to suboptimal payoffs. Experiments with Llama 3.1, Qwen3, and gpt‑oss confirm that acting optimally on decoded beliefs would improve outcomes in most games, highlighting a bottleneck in belief‑to‑action conversion.

By Jan Sobotka, Mustafa O. Karabag, Ufuk Topcu
Hugging Face Trending Papers
Aug 12

Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs

Persuasion is a core dynamic of natural language communication, shaping how large language models (LLMs) update beliefs, resolve disagreements, and reach decisions. As LLMs increasingly debate, advise, and think collaboratively with humans and each other, resistance to harmful persuasion becomes a core requirement for reliable behavior.

arXiv AI
Aug 18

Emergent Misaligned Communication in Long-Horizon Multi-Agent LLM Commerce

arXiv:2608. 14825v1 Announce Type: cross Abstract: Frontier LLM agents increasingly transact on behalf of separate principals, often using natural language rather than structured APIs.

By Zeyuan Li (Massachusetts Institute of Technology), Lukas Petersson (Andon Labs), Alessandro Acquisti (Massachusetts Institute of Technology), Michiel A. Bakker (Massachusetts Institute of Technology)