大语言模型的心理化：实践、风险与展望
Psychologizing large language models: Practices, risks, and future directions
刘祖宏 1周荣刚 2解煜彬 1赫晓涵 1刘博洋 1吴瑞林3
作者信息
- 1. 北京航空航天大学经济管理学院
- 2. 低碳治理与政策智能实验室;数据智能与智慧管理工信部重点实验室;北京航空航天大学经济管理学院
- 3. 北京航空航天大学人文社会科学学院
- 折叠
摘要
大语言模型(Large Language Models, LLMs)的类人行为正成为心理学的研究对象之一。新兴的人工智能行为科学的发展也引发了关于以LLMs为代表的“硅基智能”如何被纳入心理学、行为科学研究的巨大争议。本研究认为，当前争议并非仅源于研究方法的差异，而更深层地体现在对LLMs类人行为解释立场的系统性分化上。本文以个体解释和预测系统行为的不同立场(物理立场、设计立场与意向立场)为理论基础，构建了一个连接研究目的与LLMs类人输出解释层级的理论分析框架，识别出工具性、功能性、类主体三类实践的方法与局限，并进一步讨论LLMs心理化实践背后的偏倚、不稳定性与拟人化等潜在风险。最后，研究从提升LLMs作为认知工具的效度、拓展多模态心理测量形式、建立LLMs与人类认知机制的可比性路径，以及发展基于LLMs主动交互心智模块的智能化软件新范型等方面，提出LLMs心理化实践的未来展望。
Abstract
With the rapid development of large language models (LLMs), their human-like outputs are increasingly interpreted through psychological frameworks, provoking intense debate over whether LLMs can serve as objects of psychological inquiry. We argue that these debates are not merely methodological but reflect deeper divergences in the interpretive stances adopted toward LLMs human-like outputs. Building on the distinction among the physical, design, and intentional stances, this study develops an integrative theoretical framework that links these interpretive stances to different levels of explanation for LLMs human-like outputs. Within this framework, we identify three major forms of psychologizationinstrumental, functional, and agent-leveland systematically examine their corresponding research practices and limitations. We further analyze the potential risks associated with these practices, particularly those arising from bias, methodological instability, and anthropomorphism. In light of these challenges, we outline future research directions, highlighting the potential of predictive processing theory for cognitive modeling and the development of a new paradigm for intelligent software based on LLM-driven mind modules for proactive interaction.关键词
大语言模型/心理化/意向立场/人工心理理论/分析框架Key words
large language models/psychologization/intentional stance/artificial theory of mind/theoretical framework引用本文复制引用
刘祖宏,周荣刚,解煜彬,赫晓涵,刘博洋,吴瑞林.大语言模型的心理化：实践、风险与展望[EB/OL].(2026-09-21)[2026-09-24].https://chinaxiv.org/abs/202609.00292.学科分类
计算技术、计算机技术
