发表机构
Northeastern University; Centre for Human-Inspired Artificial Intelligence (CHIA); University of Cambridge（东北大学; 人类启发式人工智能中心; 剑桥大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过预注册实验发现，与大型语言模型短暂互动（不针对价值或说服）可暂时将用户价值优先级转向个人聚焦，主要增强自我提升，且不导致价值方向或建议趋同。
AI 中文摘要
大型语言模型越来越多地支持价值观存在冲突的决策，然而，关于与它们互动是否会改变用户优先考虑的价值，目前知之甚少。在一项预注册研究中，200名美国成年人将ChatGPT、Claude或Gemini作为思考伙伴进行互动，或阅读固定的AI生成考量。提示要求LLM在不推荐决策的情况下支持推理，且未提及任何价值。参与者为面临真实困境的人提供建议，并在互动前、互动后立即及一项任务后完成平行的PVQ-RR量表。与对照组相比，每种LLM条件都暂时将价值优先级转向个人聚焦（d=0.37-0.51），主要通过增强自我提升实现。参与者的建议保留了其交流中的词汇和含义。因此，一次既不以价值为目标也不寻求说服的简短LLM互动，可以重新定向判断期间活跃的价值，而不会在价值方向或建议上产生可检测的趋同。
英文摘要
Large language models increasingly support decisions where values are in tension, yet little is known about whether interacting with them changes which values users prioritize. In a preregistered study, 200 U.S. adults interacted with ChatGPT, Claude, or Gemini as a thinking partner or read fixed AI-generated considerations. The prompt asked LLMs to support reasoning without recommending a decision and named no values. Participants advised people facing real dilemmas and completed parallel PVQ-RR forms before, immediately after, and one task later. Each LLM condition temporarily shifted value priorities toward personal focus relative to the control (d=0.37-0.51), primarily through increased Self-Enhancement. Participants' advice retained words and meaning from their exchanges. Thus, a brief LLM interaction that neither targets values nor seeks to persuade can reorient values active during judgment without detectable convergence in value directions or advice.
