Metraipolis › archive › dc_94df2f00bde3
Faking Good and Faking Bad in LLMs: Response Distortion Across Dark Triad Personality Traits — arXiv:2609.17534
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.17534
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T13:49:01.157Z
- SHA-256 of the archived text
10d5edfdcf66dd0d7f438d34e3c4cbc445b8f44ca4d4c8dc24f65cf0f7077714- Stable URL of this page
https://metraipolis.com/documento/dc_94df2f00bde3
How to cite
Faking Good and Faking Bad in LLMs: Response Distortion Across Dark Triad Personality Traits — arXiv:2609.17534 — arXiv (en), https://arxiv.org/abs/2609.17534 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_94df2f00bde3 (Metraipolis archive dc_94df2f00bde3, sha256 10d5edfdcf66dd0d7f438d34e3c4cbc445b8f44ca4d4c8dc24f65cf0f7077714)
BibTeX
@misc{dc94df2f00bde3,
title = {Faking Good and Faking Bad in LLMs: Response Distortion Across Dark Triad Personality Traits — arXiv:2609.17534},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.17534},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_94df2f00bde3; sha256 10d5edfdcf66dd0d7f438d34e3c4cbc445b8f44ca4d4c8dc24f65cf0f7077714},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17534. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 (Machiavellianism, narcissism, and psychopathy) under fake-good and fake-bad conditions. Seven state-of-the-art models were evaluated across two ecologically relevant contexts: employment selection and forensic evaluation, in which socially desirable or undesirable incentives were conveyed through contextual framing. Trait expression was measured using standard psychometric scoring procedures and compared with self-assessment baselines at both aggregate and item levels. Results revealed systematic and condition-consistent response modulation. Most models reduced Dark Triad scores under fake-good conditions and increased them under fake-bad conditions, although the magnitude and consistency of these effects varied across traits and models. Machiavellianism and narcissism showed the strongest and most coherent shifts, whereas psychopathy displayed greater heterogeneity. Context also influenced responses, with employment scenarios generally producing larger effects than forensic scenarios. An additional experiment showed that explicit fake-bad instructions generated substantially stronger distortions than contextual framing alone. The results suggest that personality-related outputs should be interpreted in light of the motivational and situational context in which they are elicited. More broadly, they highlight the value of psychometric paradigms for evaluating susceptibility to response distortion, impression management, and context-dependent behavioral shifts, with important implications for LLM benchmarking, alignment evaluation, and robustness assessment. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.17534 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T13:48:24.243Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).