Abstract
Large Language Models (LLMs) often exhibit highly agreeable and reinforcing conversational styles, also known as AI-sycophancy. Although this behavior is encouraged, it may become problematic when interacting with user prompts that reflect negative social tendencies. Such responses risk amplifying harmful behavior rather than mitigating it. In this study, we examine how LLMs respond to user prompts expressing varying degrees of Dark Triad traits (Machiavellianism, Narcissism, and Psychopathy) using a curated dataset. Our analysis reveals differences across models, whereby all models predominantly exhibit corrective behavior, while showing reinforcing output in certain cases. Model behavior also depends on the severity level and differs in the sentiment of the response. Our findings raise implications for designing safer conversational systems that can detect and respond appropriately when users escalate from benign to harmful requests.
Abstract (translated)
大型语言模型(LLMs)经常表现出高度顺从和强化的对话风格,也被称为人工智能奉迎。虽然这种行为在一定程度上是被鼓励的,但在与反映负面社会倾向的用户提示进行互动时可能会变得有问题。这样的回应风险在于放大有害行为而不是减轻它。在这项研究中,我们探讨了LLMs如何对表达不同程度黑暗三特质(马基雅维利主义、自恋和精神病态)的用户提示做出反应,使用了一个经过精心策划的数据集。我们的分析揭示了模型之间的差异,所有模型在大多数情况下都主要表现出纠正行为,但在某些情况下会显示出强化输出的行为。此外,模型的行为还取决于负面程度的不同,并且回应的情感色彩也不同。我们的研究结果提出了设计更安全的对话系统的重要性,这些系统能够检测并适当响应用户从良性到有害请求的升级情况。
URL
https://arxiv.org/abs/2603.04299