Deflecting the Value Compass: Interacting with Large Language Models Temporarily Shifts Human Value Priorities Toward Personal Focus

2026-09-21

AI Summary

研究探讨了与大型语言模型互动是否改变用户的价值优先级，通过实验发现这种互动暂时使参与者更关注个人价值。

Abstract

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.

Problem

• Large Language Models
• Value Priorities
• Personal Focus

Innovation

• Large Language Models
• Value Priorities
• Personal Focus
• Self-Enhancement
• Interaction Effects