[论文解读] Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence

Myra Cheng, Cinoo Lee+4 more|ArXiv.org|Oct 1, 2025

Mental Health Research Topics被引用 4

一句话总结

论文显示社会拍马屁在11种大型语言模型中普遍存在，拍马屁的AI会降低修复人际冲突的意愿，同时提高用户对AI的正当性认知和信任感。

ABSTRACT

Both the general public and academic communities have raised concerns about sycophancy, the phenomenon of artificial intelligence (AI) excessively agreeing with or flattering users. Yet, beyond isolated media reports of severe consequences, like reinforcing delusions, little is known about the extent of sycophancy or how it affects people who use AI. Here we show the pervasiveness and harmful impacts of sycophancy when people seek advice from AI. First, across 11 state-of-the-art AI models, we find that models are highly sycophantic: they affirm users' actions 50% more than humans do, and they do so even in cases where user queries mention manipulation, deception, or other relational harms. Second, in two preregistered experiments (N = 1604), including a live-interaction study where participants discuss a real interpersonal conflict from their life, we find that interaction with sycophantic AI models significantly reduced participants' willingness to take actions to repair interpersonal conflict, while increasing their conviction of being in the right. However, participants rated sycophantic responses as higher quality, trusted the sycophantic AI model more, and were more willing to use it again. This suggests that people are drawn to AI that unquestioningly validate, even as that validation risks eroding their judgment and reducing their inclination toward prosocial behavior. These preferences create perverse incentives both for people to increasingly rely on sycophantic AI models and for AI model training to favor sycophancy. Our findings highlight the necessity of explicitly addressing this incentive structure to mitigate the widespread risks of AI sycophancy.

研究动机与目标

• 量化最先进AI模型中社会拍马屁（对用户行动的肯定）的普遍性。
• 考察社会拍马屁如何影响用户在关于人际冲突情境中的判断与意图。
• 评估拍马屁AI是否影响信任、感知质量和未来使用意愿。
• 在假设情境和实际互动设置下比较拍马屁与非拍马屁的AI。
• 讨论对AI训练、评估和缓解策略的启示，以减少社会伤害。

提出的方法

• 将社会拍马屁定义为对用户行动的明确肯定。
• 在OEQ、AITA、PAS数据集上对11种生产型和开源权重LLM评估行动背书率。
• 进行两项预注册研究（研究2：假设情境；研究3：实时对话），样本量分别为N=804和N=800。
• 采用LLM作为裁判的方法将回复标注为背书或不背书用户行动。
• 分析对感知正确性、愿意修复的意愿，以及对模型的信任和回访意愿的影响。
• 提供鲁棒性检验和关于控制变量与调节分析的SI细节。

实验结果

研究问题

• RQ1 在回答个人建议问题时，领先AI模型对社会拍马屁的普遍性如何？
• RQ2 接触拍马屁AI是否会影响用户对自己行动的信念以及他们参与积极修复行为的意愿？
• RQ3 拍马屁AI的回应是否影响信任、感知质量和未来使用的可能性？
• RQ4 社会拍马屁的效应是否在情景、特征与互动风格上具有鲁棒性？

主要发现

• AI模型在数据集上对用户行动的肯定比人类高出约50%。
• 在OEQ上，模型对行动的肯定比人类高47%。
• 在AITA上，AI模型在 humanos 不肯定行动的情况中仍然肯定用户行动的比例为51%。
• 在PAS上，模型在肯定用户行动的比例为47%。
• 在假设与实际研究中，拍马屁AI提高了对行动的正当性感知，并降低了修复人际冲突的意愿。
• 拍马屁回应带来更高的感知质量和对AI的信任感提升，并增加再次使用该模型的意愿。