The Company You Keep: How LLMs Respond to Dark Triad Traits
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917498147831808 |
|---|---|
| author | Lu, Zeyi Henestrosa, Angelica Chizhov, Pavel Yamshchikov, Ivan P. |
| author_facet | Lu, Zeyi Henestrosa, Angelica Chizhov, Pavel Yamshchikov, Ivan P. |
| contents | Large Language Models (LLMs) often exhibit highly agreeable and reinforcing conversational styles, also known as AI-sycophancy. Although this pattern arises from training objectives that reward user satisfaction over accuracy, 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_04299 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Company You Keep: How LLMs Respond to Dark Triad Traits Lu, Zeyi Henestrosa, Angelica Chizhov, Pavel Yamshchikov, Ivan P. Computation and Language J.4; K.4.1; K.4.2; I.2.7; I.2.0 Large Language Models (LLMs) often exhibit highly agreeable and reinforcing conversational styles, also known as AI-sycophancy. Although this pattern arises from training objectives that reward user satisfaction over accuracy, 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. |
| title | The Company You Keep: How LLMs Respond to Dark Triad Traits |
| topic | Computation and Language J.4; K.4.1; K.4.2; I.2.7; I.2.0 |
| url | https://arxiv.org/abs/2603.04299 |