LLM Wardens: Mitigating Adversarial Persuasion with Third-Party Conversational Oversight

ArXi:2605.08321v1 Announce Type: cross LLMs are increasingly capable of persuasion, which raises the question of how to protect users against manipulation. In a preregistered user study (N=120) across four decision-making scenarios, we find that an adversarial LLM with a hidden goal succeeds in steering users' decisions 65.4% of the time. We then