解构大语言模型中的欺骗与幻觉故障
Disentangling Deception and Hallucination Failures in LLMs
AI总结：
本研究提出一种机制导向的视角，解构大语言模型中幻觉与欺骗的不同故障机制，通过受控环境分析四种行为案例，揭示知识存在与行为表达的分离。
摘要：
大语言模型（LLMs）的故障往往从行为角度进行分析，其中事实性问答中的错误输出通常与知识缺失相关。在本工作中，聚焦于基于实体的事实性查询，我们建议这种观点可能混杂了不同的故障机制，并提出一种内部、机制导向的视角，将知识存在与行为表达分开。在此框架下，幻觉和欺骗对应于两种质上不同的故障模式，可能在输出层面看起来相似，但其底层机制不同。为研究这一区别，我们构建了一个以实体为中心的事实性问题受控环境，在其中保留知识的同时，有选择地改变行为表达，从而系统分析四种行为案例。我们通过表示分离性、稀疏可解释性和推理时激活引导来分析这些故障模式。
英文摘要：
Failures in large language models (LLMs) are often analyzed from a behavioral perspective, where incorrect outputs in factual question answering are commonly associated with missing knowledge. In this work, focusing on entity-based factual queries, we suggest that such a view may conflate different failure mechanisms, and propose an internal, mechanism-oriented perspective that separates Knowledge Existence from Behavior Expression. Under this formulation, hallucination and deception correspond to two qualitatively different failure modes that may appear similar at the output level but differ in their underlying mechanisms. To study this distinction, we construct a controlled environment for entity-centric factual questions in which knowledge is preserved while behavioral expression is selectively altered, enabling systematic analysis of four behavioral cases. We analyze these failure modes through representation separability, sparse interpretability, and inference-time activation steering.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
