Paper Reading AI Learner

The Company You Keep: How LLMs Respond to Dark Triad Traits

2026-03-04 17:19:22
Zeyi Lu, Angelica Henestrosa, Pavel Chizhov, Ivan P. Yamshchikov

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

PDF

https://arxiv.org/pdf/2603.04299.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Time_Series Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot