Exploring a Gamified Personality Assessment Method through Interaction with LLM Agents Embodying Different Personalities

TL;DR

This paper introduces a gamified, interactive framework using LLM-powered virtual agents with multiple personalities to assess human traits based on Big Five theory, showing improved accuracy and interpretability.

Contribution

It presents the Multi-PR GPA framework that leverages multi-personality LLM agents for low-intrusion, interactive personality assessment with demonstrated effectiveness.

Findings

The approach effectively assesses personality traits through interactive games.

Multi-PR GPA outperforms traditional methods in accuracy.

Systematic biases in LLM assessments can be mitigated with multi-context aggregation.

Abstract

The low-intrusion and automated personality assessment is receiving increasing attention in psychology and human-computer interaction fields. This study explores an interactive approach for personality assessment, focusing on the multiplicity of personality representation. We propose a framework of Gamified Personality Assessment through Multi-Personality Representations (Multi-PR GPA). The framework leverages Large Language Models to empower virtual agents with different personalities. These agents elicit multifaceted human personality representations through engaging in interactive games. Drawing upon the multi-type textual data generated throughout the interaction, it achieves personality assessments with interpretable insights. Grounded in the classic Big Five personality theory, we developed a prototype system and conducted a user study to evaluate the efficacy of Multi-PR GPA. The results affirm the effectiveness of our approach in personality assessment and demonstrate its superior performance when considering the multiplicity of personality representation. Error structure analysis further revealed systematic assessment biases in LLMs, which multi-context aggregation partially mitigated.