Timezone: »

Spotlight Poster
Evaluating and Inducing Personality in Pre-trained Language Models
Guangyuan Jiang · Manjie Xu · Song-Chun Zhu · Wenjuan Han · Chi Zhang · Yixin Zhu

Wed Dec 13 08:45 AM -- 10:45 AM (PST) @ Great Hall & Hall B1+B2 #321
Standardized and quantified evaluation of machine behaviors is a crux of understanding LLMs. In this study, we draw inspiration from psychometric studies by leveraging human personality theory as a tool for studying machine behaviors. Originating as a philosophical quest for human behaviors, the study of personality delves into how individuals differ in thinking, feeling, and behaving. Toward building and understanding human-like social machines, we are motivated to ask: Can we assess machine behaviors by leveraging human psychometric tests in a **principled** and **quantitative** manner? If so, can we induce a specific personality in LLMs? To answer these questions, we introduce the Machine Personality Inventory (MPI) tool for studying machine behaviors; MPI follows standardizedpersonality tests, built upon the Big Five Personality Factors (Big Five) theory and personality assessment inventories. By systematically evaluating LLMs with MPI, we provide the first piece of evidence demonstrating the efficacy of MPI in studying LLMs behaviors. We further devise a Personality Prompting (P$^2$) method to induce LLMs with specific personalities in a **controllable** way, capable of producing diverse and verifiable behaviors. We hope this work sheds light on future studies by adopting personality as the essential indicator for various downstream tasks, and could further motivate research into equally intriguing human-like machine behaviors.

Author Information

Guangyuan Jiang (MIT / Peking University)
Manjie Xu (Beijing Institute of Technology)
Song-Chun Zhu (UCLA)
Wenjuan Han (Beijing Jiaotong University)
Chi Zhang (University of California, Los Angeles)
Yixin Zhu (Peking University)

More from the Same Authors