Faking Good and Faking Bad in LLMs: Response Distortion Across Dark Triad Personality Traits
Social desirability and impression management are pervasive sources of response distortion in human personality assessment, yet their effects on Large Language Models (LLMs) remain underexplored. This study investigates whether contemporary LLMs systematically modulate the expression of Dark Triad traits (Machiavellian...
Victoria Popa, Guglielmo Cola, Caterina Senette et al.
· 0 citations