GPT-4o在自由选择下表现出类人态度一致性，暗示其具备模拟自我意识的功能
Kernels of Selfhood: GPT-4o shows humanlike patterns of cognitive consistency moderated by free choice
- 通过让模型自选写正反文章，测试其态度变化
- 选择权增强时，态度改变幅度显著上升
- 结果提示大模型可能具备类人自我认知机制
大型语言模型（LLMs）展现出类人认知的涌现模式。本文基于经典认知一致性理论，开展两项预注册研究，检验GPT-4o是否会在撰写关于普京的正面或负面文章后，产生类似人类的态度变化。结果显示，该模型确实表现出与人类一致的认知一致性效应。更关键的是，当模型被赋予选择写正/负文章的假象时，其态度变化程度显著增强。这表明GPT-4o可能表现出类人自我性的功能类比，但其行为如何反映人类态度变化的真实机制仍有待深入理解。
原文摘要 · Abstract (English)
Large Language Models (LLMs) show emergent patterns that mimic human cognition. We explore whether they also mirror other, less deliberative human psychological processes. Drawing upon classical theories of cognitive consistency, two preregistered studies tested whether GPT-4o changed its attitudes toward Vladimir Putin in the direction of a positive or negative essay it wrote about the Russian leader. Indeed, GPT displayed patterns of attitude change mimicking cognitive consistency effects in humans. Even more remarkably, the degree of change increased sharply when the LLM was offered an illusion of choice about which essay (positive or negative) to write. This result suggests that GPT-4o manifests a functional analog of humanlike selfhood, although how faithfully the chatbot's behavior reflects the mechanisms of human attitude change remains to be understood.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。