通过人类之眼审视人工智能：在机器心理学中探究认知理论
AI Through the Human Lens: Investigating Cognitive Theories in Machine Psychology
AI总结：
本文通过四个心理学框架研究LLMs的认知模式，发现其在叙述生成、框架偏差、道德判断和自我矛盾等方面表现出与人类相似但受训练数据影响的行为特征。
摘要：
我们研究大型语言模型（LLMs）是否在四个已建立的心理学框架下表现出人类般的认知模式：主题知觉测试（TAT）、框架偏差、道德基础理论（MFT）和认知失调。我们使用结构化提示和自动化评分评估了多个专有和开源模型。我们的发现表明，这些模型往往能生成连贯的叙述，表现出对积极框架的易感性，表现出与自由/压迫相关道德判断，并在大量理性化下表现出自我矛盾。这些行为反映了人类的认知倾向，但受其训练数据和对齐方法的影响。我们讨论了这对AI透明度、伦理部署以及未来连接认知心理学和AI安全工作的意义。
英文摘要：
We investigate whether Large Language Models (LLMs) exhibit human-like cognitive patterns under four established frameworks from psychology: Thematic Apperception Test (TAT), Framing Bias, Moral Foundations Theory (MFT), and Cognitive Dissonance. We evaluated several proprietary and open-source models using structured prompts and automated scoring. Our findings reveal that these models often produce coherent narratives, show susceptibility to positive framing, exhibit moral judgments aligned with Liberty/Oppression concerns, and demonstrate self-contradictions tempered by extensive rationalization. Such behaviors mirror human cognitive tendencies yet are shaped by their training data and alignment methods. We discuss the implications for AI transparency, ethical deployment, and future work that bridges cognitive psychology and AI safety
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
