Who is ChatGPT? Benchmarking LLMs' Psychological Portrayal Using PsychoBench

Item Type Preprint Author Jen-tse Huang Author Wenxuan Wang Author Eric John Li Author Man Ho Lam Author Shujie Ren Author Youliang Yuan Author Wenxiang Jiao Author Zhaopeng Tu Author Michael R. Lyu URL http://arxiv.org/abs/2310.01386 Date 2024-01-22 Extra arXiv:2310.01386 [cs] DOI 10.48550/arXiv.2310.01386 Accessed 2025-01-10 20:22:16 Library Catalog arXiv.org 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. Short Title Who is ChatGPT? Repository arXiv Archive ID arXiv:2310.01386