Rediscovering the Latent Dimensions of Personality with Large Language Models as Trait Descriptors

TL;DR

This paper demonstrates that large language models implicitly encode core personality traits, which can be uncovered through singular value decomposition of trait-related probabilities, enabling accurate personality assessment without explicit questionnaires.

Contribution

The study introduces a novel method to extract latent personality dimensions from LLMs using SVD, revealing core traits and improving prediction accuracy over existing techniques.

Findings

LLMs implicitly encode Big Five personality traits.

Top-5 factors explain 74.3% of variance in latent space.

Personality prediction accuracy improves up to 21%.

Abstract

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.