Self-assessment, Exhibition, and Recognition: a Review of Personality in Large Language Models

Sep 17, 2026

Large language models exhibit increasingly human-like behavior in text interactions, motivating extensive research into whether and how LLMs reflect human personality. This interdisciplinary area remains fragmented due to varying psychological theories, diverse psychometric instruments, and rapid proliferation of different LLM architectures, making holistic comparison and real-world application difficult. The paper reviews studies by organizing them into self-assessment, exhibition, and recognition, analyzing methods, comparing solutions, and outlining findings, open challenges, and future directions, with curated public resources.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages19

Reading Time48 min

AccessFree to download

Introduction

Diversity of research focuses

Psychometrics and personality models

Investigated LLMs

Self-assessment

Likert-scale questionnaires

Text analysis for responses

Exhibition

Editing LLM’s personality

Inducing LLM’s personality

Recognition

Personality recognition by LLMs

LLM-enhanced personality recognition

Self-assessment, Exhibition, and Recognition: a Review of Personality in Large Language Models Zhiyuan Wen1 , Yu Yang1 , Jiannong Cao1 , Haoming Sun1 , Ruosong Yang1 , Shuaiqi Liu2 1The Hong Kong Polytechnic University, Kowloon, Hong Kong, China 2Huawei Technologies Co., Ltd, Shenzhen, China {zyuanwen, cs-yu .yang, [jiannong.cao} @poly.edu.hk](jiannong.cao} @poly.edu.hk)[haoming.sun@connect.polyu.hk](haoming.sun@connect.polyu.hk) [rsong.yang@polyu.edu.hk](rsong.yang@polyu.edu.hk) [liushuaiqi@huawei.com](liushuaiqi@huawei.com) arXiv :2406 . 17624v1 [ cs .CL] 25 Jun 2024 Abstract As large language models (LLMs) appear to behave increasingly human-like in text-based interactions, more and more researchers become interested in investigating personality in LLMs. However, the diversity of psychological personality research and the rapid development of LLMs have led to a broad yet fragmented landscape of studies in this interdisciplinary field. Extensive studies across different research focuses, different personality psychometrics, and different LLMs make it challenging to have a holistic overview and further pose difficulties in applying findings to real-world applications. In this paper, we present a comprehensive review by categorizing current studies into three research problems: self-assessment, exhibition, and recognition, based on the intrinsic characteristics and external manifestations of personality in LLMs. For each problem, we provide a thorough analysis and conduct in-depth comparisons of their corresponding solutions. Besides, we summarize research findings and open challenges from current studies and further discuss their underlying causes. We also collect extensive publicly available resources to facilitate interested researchers and developers. Lastly, we discuss the potential future research directions and application scenarios. Our paper is the first comprehensive survey of up-to-date literature on personality in LLMs. By presenting a clear taxonomy, in-depth analysis, promising future directions, and extensive resource collections, we aim to provide a better understanding and facilitate further advancements in this emerging field. 1 Introduction Large Language Models (LLMs) have exhibited impressive language comprehension and generation capabilities, enabling them to conduct coherent, human-like conversations with users. These remarkable progress have led to a wide range of applications (Chen et al., 2023 ; Zheng et al., 2023 ; He et al., 2023) and also ignited a growing interest in exploring the personality in LLMs. Personality is described as the enduring characteristics that shape an individual’s thoughts, emotions, and behaviors (Mischel et al., 2007) . In the context of LLMs, researchers are curious about whether LLMs have intrinsic personality traits or how well can LLMs handle personality-related tasks in interaction. These investigations facilitate understanding the psychological portrayal of LLMs (Huang et al., 2023b) and further constructing AI systems that are more transparent, safe, and trustworthy (Safdari et al., 2023) . In light of this, numerous studies have emerged in this interdisciplinary field over the past two years, as shown in Appendix A. However, the diversity of psychological personality research (Hodo, 2006) and the rapid development of LLMs make it difficult to not only obtain a comprehensive overview of this research area but also compare different methods, derive general conclusions, and apply findings to real-world applications. Specifically, current studies exhibit a hodgepodge in: • Research Focuses: The topic of personality in LLMs encompasses various aspects, e.g., LLMs’ personality assessment, or LLMs’awareness of users’ personalities. Despite this breadth, most studies are only interested in particular aspects. • Psychometrics: Different studies focus on different personality models (e.g., Big-five (Digman, 1990) and the Myers-Briggs

FAQs

How does the paper organize research on personality in large language models?

It categorizes existing work into three research problems: self-assessment, exhibition, and recognition, based on intrinsic characteristics and external manifestations of personality in LLMs.

Why is it difficult to compare findings across current personality-in-LLM studies?

Studies vary widely in research focus, personality psychometrics, and which LLMs are investigated, creating a fragmented landscape that hampers holistic overview and general conclusions.

What does the self-assessment section cover?

It covers approaches such as Likert-scale questionnaires and text analysis of responses used to evaluate personality-related aspects of LLM behavior.

Sep 17, 2026

Uploaded by Nguyễn Văn Học