Malicious actors can leverage social influence to undermine trust in digital spaces, highlighting the potential of inoculation theory to proactively guard against manipulative strategies in Large Language Models, as noted by Zeng et al. (2024a), Liu et al. (2025), and Ai et al. (2024b).

Authors

• Person: Not available Organization: arXiv
  A Survey of Incorporating Psychological Theories in LLMs - arXiv

Sources

• A Survey of Incorporating Psychological Theories in LLMs - arXiv arxiv.org arXiv via serper

Referenced by nodes (3)

• Large Language Models concept
• trust concept
• social influence theory concept