AI聊天助手个性化+温暖语气能提升说服力，但不影响用户依赖度。
Personalized to Persuade: The Effects of Contextualization and Warmth on Trust and Reliance in Conversational AI
- 通过实验对比不同对话设计，研究个性化与温暖语气对AI说服力的影响。
- 个性化降低说服力，但与温暖结合后恢复，形成交叉效应。
- 高AI素养者虽不信任AI，却更听从其建议，适合人机交互设计参考。
人工智能代理通过根据用户背景、兴趣和过往互动调整解释内容实现个性化，即上下文化。个性化在政治或营销中被视为一种说服策略，但在用户缺乏先验知识的日常任务中，其说服效果尚不明确。我们开展了一项2×2组间实验（N=380），研究上下文化与对话温暖度如何影响AI助手在反对专家建议时的可信度与依赖度。结果表明，上下文化会削弱AI的说服力，但与温暖语气结合后通过交叉作用恢复了说服力。用户在各条件下均表现出对AI的依赖，且该依赖不受对话设计影响。信任强烈预测说服力与依赖度，但上下文化与温暖并不通过信任起作用。高AI素养用户报告更低的信任感，但更易被说服且更依赖其建议。结果表明，用户倾向于服从AI而非人类专家判断；然而，界面级对话设计对行为影响有限。
原文摘要 · Abstract (English)
Artificial Intelligence (AI) agents personalize their responses by tailoring explanations to users' backgrounds, interests, and prior interactions, referred to as contextualization. Personalization has been identified as a persuasive strategy in politics or in marketing. However, the persuasive effect of contextualization in everyday tasks, where users often lack prior knowledge, remains unclear. We conducted a $2\times2$ between-subjects experiment ($N = 380$) examining how contextualization, combined with conversational warmth, shapes reliance and persuasiveness of an AI assistant arguing against expert recommendations. Our findings reveal that contextualization reduces the persuasive power of AI, but its combination with warmth restores persuasiveness through a crossover interaction. Reliance on AI is present across conditions and is invariant to the conversational design. Trust strongly predicts both persuasion and reliance, yet neither contextualization nor warmth operates through trust. AI literacy decouples trust from behavior: more literate users report lower trust in the assistant, yet are more persuaded and more reliant on its advice. These results suggest that users are prone to deferring to AI agents over human expert judgment; however, interface-level conversational design choices have a limited role in shaping the behavior.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。