用对话推断人格特质，分步推理更准。
Investigating Large Language Models in Inferring Personality Traits from User Conversations
- 先预测问卷题项再推人格，比直接推更准
- 有抑郁症状者性格变化被模型更敏感捕捉
- 适合心理学与AI交叉研究者参考
大型语言模型（LLMs）在多个领域展现出类人能力，包括心理评估。本研究评估GPT-4o和GPT-4o mini在零样本提示条件下，能否从用户对话中推断大五人格特质并生成大五人格问卷-10项版（BFI-10）题项得分。结果表明，引入中间步骤——先提示生成BFI-10题项得分，再计算人格特质——显著提升准确率，并更接近金标准。该结构化方法凸显了借助心理学框架提升预测精度的重要性。此外，基于抑郁症状存在与否的组间比较显示：在有至少一项抑郁症状的参与者中，GPT-4o mini对神经质和尽责性等特质的变化更为敏感；而GPT-4o则在跨组别情境下展现更细致的解读能力。这些发现表明LLMs可有效分析真实世界心理数据，为人工智能与心理学交叉研究提供坚实基础。
原文摘要 · Abstract (English)
Large Language Models (LLMs) are demonstrating remarkable human like capabilities across diverse domains, including psychological assessment. This study evaluates whether LLMs, specifically GPT-4o and GPT-4o mini, can infer Big Five personality traits and generate Big Five Inventory-10 (BFI-10) item scores from user conversations under zero-shot prompting conditions. Our findings reveal that incorporating an intermediate step--prompting for BFI-10 item scores before calculating traits--enhances accuracy and aligns more closely with the gold standard than direct trait inference. This structured approach underscores the importance of leveraging psychological frameworks in improving predictive precision. Additionally, a group comparison based on depressive symptom presence revealed differential model performance. Participants were categorized into two groups: those experiencing at least one depressive symptom and those without symptoms. GPT-4o mini demonstrated heightened sensitivity to depression-related shifts in traits such as Neuroticism and Conscientiousness within the symptom-present group, whereas GPT-4o exhibited strengths in nuanced interpretation across groups. These findings underscore the potential of LLMs to analyze real-world psychological data effectively, offering a valuable foundation for interdisciplinary research at the intersection of artificial intelligence and psychology.
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。