2 papers
cs.CL2026
Faking Good and Faking Bad in LLMs: Response Distortion Across Dark Triad Personality Traits
Victoria Popa, Guglielmo Cola, Caterina Senette +1
Social desirability and impression management are pervasive sources of response distortion in human personality assessment, yet their effects on Large Language Models (LLMs) remain…
cs.SI2025
From Toxicity to Conformity: Adaptive user behavior to social norms in Telegram communities
Lorenzo Alvisi, Victoria Popa, Guglielmo Cola +2
Toxic and antisocial user behavior on social media platforms has received considerable scholarly attention due to its detrimental effects on society. This study takes a holistic pe…