Who is ChatGPT? Benchmarking LLMs' Psychological Portrayal Using PsychoBench

TL;DR

This paper introduces PsychoBench, a comprehensive framework for evaluating psychological traits in large language models, revealing insights into their personalities, emotions, and intrinsic natures through diverse testing methods.

Contribution

We propose PsychoBench, the first systematic framework to assess psychological aspects of LLMs across multiple categories, including personality, relationships, motivation, and emotions.

Findings

Different LLMs exhibit varying psychological profiles.

Jailbreak methods reveal intrinsic traits of models.

PsychoBench is publicly accessible for further research.

Abstract

Large Language Models (LLMs) have recently showcased their remarkable capacities, not only in natural language processing tasks but also across diverse domains such as clinical medicine, legal consultation, and education. LLMs become more than mere applications, evolving into assistants capable of addressing diverse user requests. This narrows the distinction between human beings and artificial intelligence agents, raising intriguing questions regarding the potential manifestation of personalities, temperaments, and emotions within LLMs. In this paper, we propose a framework, PsychoBench, for evaluating diverse psychological aspects of LLMs. Comprising thirteen scales commonly used in clinical psychology, PsychoBench further classifies these scales into four distinct categories: personality traits, interpersonal relationships, motivational tests, and emotional abilities. Our study examines five popular models, namely text-davinci-003, gpt-3.5-turbo, gpt-4, LLaMA-2-7b, and LLaMA-2-13b. Additionally, we employ a jailbreak approach to bypass the safety alignment protocols and test the intrinsic natures of LLMs. We have made PsychoBench openly accessible via https://github.com/CUHK-ARISE/PsychoBench.