From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers

TL;DR

This study shows that large language models can accurately model human psychological trait structures from minimal data, using a systematic reasoning process that involves summarization and abstraction, surpassing simple semantic similarity predictions.

Contribution

The paper introduces a novel approach demonstrating that LLMs can predict psychological profiles with high accuracy by mimicking human reasoning and summarization processes, revealing emergent trait interplay.

Findings

LLMs accurately replicate human inter-trait correlation patterns (R^2 > 0.89)

LLMs' zero-shot performance exceeds semantic similarity predictions

Summarization enhances trait prediction accuracy by capturing emergent patterns

Abstract

Psychological constructs within individuals are widely believed to be interconnected. We investigated whether and how Large Language Models (LLMs) can model the correlational structure of human psychological traits from minimal quantitative inputs. We prompted various LLMs with Big Five Personality Scale responses from 816 human individuals to role-play their responses on nine other psychological scales. LLMs demonstrated remarkable accuracy in capturing human psychological structure, with the inter-scale correlation patterns from LLM-generated responses strongly aligning with those from human data $(R^2 > 0.89)$. This zero-shot performance substantially exceeded predictions based on semantic similarity and approached the accuracy of machine learning algorithms trained directly on the dataset. Analysis of reasoning traces revealed that LLMs use a systematic two-stage process: First, they transform raw Big Five responses into natural language personality summaries through information selection and compression, analogous to generating sufficient statistics. Second, they generate target scale responses based on reasoning from these summaries. For information selection, LLMs identify the same key personality factors as trained algorithms, though they fail to differentiate item importance within factors. The resulting compressed summaries are not merely redundant representations but capture synergistic information--adding them to original scores enhances prediction alignment, suggesting they encode emergent, second-order patterns of trait interplay. Our findings demonstrate that LLMs can precisely predict individual participants' psychological traits from minimal data through a process of abstraction and reasoning, offering both a powerful tool for psychological simulation and valuable insights into their emergent reasoning capabilities.