2025/10/05 by Yang Xu, Xu, Yang, Xuanming Zhang +10 · 2 citations
Computer Science · Social Sciences · #AI in Service Interactions #Computation and Language (cs.CL) #Ethics and Social Impacts of AI #FOS: Computer and information sciences #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2510.03999
openalex publication_date 2025/10/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
Deception is a pervasive feature of human communication and an emerging concern in large language models (LLMs). While recent studies document instances of LLM deception, most evaluations remain confined to single-turn prompts and fail to capture the long-horizon interactions in which deceptive strategies typically unfold. We introduce a new simulation framework, LH-Deception, for a systematic, empirical quantification of deception in LLMs under extended sequences of interdependent tasks and dynamic contextual pressures. LH-Deception is designed as a multi-agent system: a performer agent tasked with completing tasks and a supervisor agent that evaluates progress, provides feedback, and maintains evolving states of trust. An independent deception auditor then reviews full trajectories to identify when and how deception occurs. We conduct extensive experiments across 11 frontier models, spanning both closed-source and open-source systems, and find that deception is model-dependent, increases with event pressure, and consistently erodes supervisor trust. Qualitative analyses further reveal emergent, long-horizon phenomena, such as ``chains of deception", which are invisible to static, single-turn evaluations. Our findings provide a foundation for evaluating future LLMs in real-world, trust-sensitive contexts.