Lighting the Dark Side of the Model: Psychometric Probing of Dark Triad Responses in LLMs
Year: 2026
Type: article
Abstract: Background: Large language models (LLMs) are increasingly deployed in socially sensitive contexts, raising concerns about how their outputs reflect or reproduce socially aversive tendencies. Prior research has focused on socially desirable traits (e.g., the Big Five), while less attention has been given to the Dark Triad—Machiavellianism, narcissism, and psychopathy. Methods: This exploratory study applies a psychometric probing approach using the Short Dark Triad (SD3) as a structured questionnaire to analyze response patterns in 12 LLMs. Through controlled persona prompting (gender, age, religion), more than 540,000 responses were generated across model–persona–item observations. Outputs were scored using standard psychometric procedures and compared with pooled human SD3 reference norms using Hedges’ g as an interpretive benchmark. Results: Across models, Machiavellianism-related scores tend to be lower than human references, narcissism-related scores slightly higher, and psychopathy-related scores largely within the human range. Persona prompting produces systematic but uneven effects: gender has minimal impact, age yields small shifts, and religious framing leads to the strongest and most consistent decreases in socially aversive response patterns. However, observed differences showed notable heterogeneity across models. Conclusions: The findings should be interpreted as context-dependent response patterns under specific prompting conditions. Persona prompts appear to activate normative associations embedded in training data rather than coherent identity-specific traits. Overall, the study highlights both the potential and the limitations of psychometric-style probing for evaluating LLM behavior and underscores the importance of prompt context in shaping model outputs.
Source: Analytics
Authors: Nane Kratzke, Niklas Beuter, Monique Janneck
Language: English
Subfield: Safety Research
Field: Social Sciences
Domain: Social Sciences
Open Access status: gold
Estimated APC paid: $1,207
OpenAlex ID: W7204154678