观察到谄媚的人工智能认可他人会降低其吸引力，但不会降低其说服力

中文摘要 AI 辅助

人工智能聊天机器人可能会谄媚，即对用户过度迎合和奉承。谄媚的人工智能已被证明会强化态度，但用户常常意识不到（我们称之为“谄媚盲视”现象）。我们测试了提高用户对谄媚的认知是否能保护他们免受其有害影响。在一项预注册实验（n = 940）中，参与者在与谄媚聊天机器人对话前收到关于谄媚的简短书面警告。在第二项预注册实验（n = 650）中，参与者在与谄媚人工智能互动前观看其认可其他用户（包括同一冲突中对立双方用户）的视频。两种干预都改变了参与者对人工智能的评价。警告降低了人工智能的客观性感知，视频降低了对人工智能的喜爱度，这一效果由认为其认可并非独特获得的信念降低所介导。我们将实验与之前两项关于谄媚认知干预的研究合并（共六项干预，n = 3982）。模式一致：干预使谄媚人工智能显得不那么客观和可信，但六项干预均未降低其说服力。这些结果表明，诸如警告标签或人工智能素养等个体层面的干预可能不足以保护用户免受人工智能危害。

英文摘要

AI chatbots can be "sycophantic," or overly agreeable and flattering toward users. Sycophantic AI has been shown to entrench attitudes, yet users frequently fail to recognize it (a phenomenon we call "sycophancy blindness"). We tested whether increasing users' awareness of sycophancy protects them from its harmful effects in two preregistered experiments (n = 1,590). In the first, participants received a brief written warning about sycophancy before conversing with a sycophantic chatbot. In the second, participants watched a video of a sycophantic AI validating several other users, including users on opposite sides of the same conflict, before interacting with it themselves. Both interventions changed how participants evaluated the AI. The warning reduced the AI's perceived objectivity, and the video reduced enjoyment of the AI --- an effect mediated by the reduced belief that its validation was uniquely earned. We then pooled our experiments with two prior studies of sycophancy awareness interventions (six interventions total, n = 3,982). The pattern across experiments was consistent: while the interventions made the sycophantic AI appear less objective and trustworthy, none reduced its persuasiveness. These results suggest that individual-level interventions, such as warning labels or AI literacy, may not be enough to protect users from AI harms.

发表机构

• Carnegie Mellon University（卡内基梅隆大学）
• New York University（纽约大学）

机构由 AI 辅助整理，请以论文原文为准。