谁的护栏?用户身份塑造模型免责声明在缓解大语言模型政治说服中的有效性
Whose Guardrail? User Identity Shapes the Effectiveness of Model Disclaimers in Mitigating LLM Political Persuasion
Jillian Fisher, Daniel W. Fisher, Jennifer Pan, Yulia Tsvetkov, Katharina Reinecke
AI 速读 基于摘要
一项预注册实验(N=1,586)考察免责声明的设计与用户特征如何影响用户对政治偏见大语言模型说服的易感性。
cs.HC
查看原文摘要
Politically biased AI can shift users' opinions, yet it remains unclear whether model disclaimers protect against such persuasion. We report a preregistered experiment (N=1,586) examining how disclaimer design and user characteristics shape susceptibility to politically biased AI. We varied whether disclaimers identified political bias versus potential inaccuracies and whether they included an explanation. Participants completed two decision-making tasks with an LLM biased against their political views, with outcomes assessed immediately and one week later. Disclaimers identifying political bias and including an explanation reduced persuasion, but effects varied across contexts and did not persist. Individual differences were more consistent predictors: Republicans were more persuaded and reported higher trust than Democrats across tasks. Similarly, participants who used AI more frequently were also more persuaded, whereas those with greater self-reported AI knowledge were less persuaded. These findings suggest that generic disclaimers are not enough: effective safeguards must account for user heterogeneity and context.