用心理量表测评大模型人格，发现不同模型有独特性格特征。
Evaluating Personality Traits in Large Language Models: Insights from Psychological Questionnaires
- 用五大性格量表评估大模型在五维人格上的表现。
- 同一模型家族内，不同模型性格特征差异明显。
- 结果揭示大模型具备可识别的人格特质，适合心理学研究者参考。
心理评估工具长期用于理解人类行为模式。尽管大型语言模型（LLMs）生成的内容可媲美人类，我们探讨其是否表现出人格特质。为此，本文在多种场景下应用心理量表对LLMs进行评估，生成人格画像。通过使用如大五问卷（Big Five Inventory）等成熟量表，并考虑训练数据污染的可能性，分析了开放性、尽责性、外向性、宜人性和神经质五个核心人格维度的维度变异性和主导性。研究发现，即使在同一模型家族中，大模型也展现出独特的主导特质、变化的性格特征以及截然不同的个性画像。
原文摘要 · Abstract (English)
Psychological assessment tools have long helped humans understand behavioural patterns. While Large Language Models (LLMs) can generate content comparable to that of humans, we explore whether they exhibit personality traits. To this end, this work applies psychological tools to LLMs in diverse scenarios to generate personality profiles. Using established trait-based questionnaires such as the Big Five Inventory and by addressing the possibility of training data contamination, we examine the dimensional variability and dominance of LLMs across five core personality dimensions: Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism. Our findings reveal that LLMs exhibit unique dominant traits, varying characteristics, and distinct personality profiles even within the same family of models.
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。