用LLM的输出概率挖掘隐藏人格特征，无需问卷即可预测五大性格维度。
Rediscovering the Latent Dimensions of Personality with Large Language Models as Trait Descriptors
- 通过SVD分析词汇概率，从LLM中提取潜在人格维度。
- 识别出五大核心人格特质，解释了74.3%的潜变量方差。
- 相比微调模型提升5%，比直接评分高21%，适合心理测量研究者。
利用大语言模型（LLMs）评估人格特质已成为一个有趣且具挑战性的研究方向。以往方法依赖于显式的问卷调查，通常基于五大人格模型。我们提出假设：当建模下一个词时，LLMs 隐式编码了人格概念。为验证此假设，本文提出一种新方法，通过将特质描述性形容词的对数概率进行奇异值分解（SVD），揭示LLM中的潜在人格维度。实验表明，即使不使用直接问卷输入，LLM仍能“重新发现”外向性、宜人性、尽责性、神经质和开放性等核心人格特质。前五个主成分对应五大人格维度，解释了潜空间中74.3%的方差。此外，可利用提取的主成分对五大维度进行人格评估，相较于微调模型平均准确率提升5%，相较直接基于LLM的评分技术提升高达21%。
原文摘要 · Abstract (English)
Assessing personality traits using large language models (LLMs) has emerged as an interesting and challenging area of research. While previous methods employ explicit questionnaires, often derived from the Big Five model of personality, we hypothesize that LLMs implicitly encode notions of personality when modeling next-token responses. To demonstrate this, we introduce a novel approach that uncovers latent personality dimensions in LLMs by applying singular value de-composition (SVD) to the log-probabilities of trait-descriptive adjectives. Our experiments show that LLMs "rediscover" core personality traits such as extraversion, agreeableness, conscientiousness, neuroticism, and openness without relying on direct questionnaire inputs, with the top-5 factors corresponding to Big Five traits explaining 74.3% of the variance in the latent space. Moreover, we can use the derived principal components to assess personality along the Big Five dimensions, and achieve improvements in average personality prediction accuracy of up to 5% over fine-tuned models, and up to 21% over direct LLM-based scoring techniques.
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。