Originated as a philosophical quest, personality discerns how individuals
differ from each other in terms of thinking, feeling, and behaving. Towards
building social machines that work with humans on a daily basis, we are
motivated to ask: (1) Do existing pre-trained language models possess
personality, akin to their human counterpart? If so, (2) how can we evaluate
them? Further, given this evaluation framework, (3) how can we induce a certain
personality in a fully controllable fashion? To tackle these three questions,
we propose the Machine Personality Inventory (MPI) dataset for evaluating the
machine personality; MPI follows standardized personality tests, built upon the
Big Five Personality Factors (Big Five) theory and personality assessment
inventories. By evaluating models with MPI, we provide the first piece of
evidence showing the existence of personality in pre-trained language models.
We further devise a Chain Prompting method to induce the language model with a
specific personality in a controllable manner, capable of producing diversified
behaviors. We hope to shed light on future studies by adopting personality as
the essential psychological guidance for various downstream tasks, building
more human-like and in situ dialogue agents.

这篇论文提出了 Machine Personality Inventory（MPI）数据集，该数据集以 Big Five Personality Factors 理论和人格评估清单为基础，旨在评估预先培训的语言模型的人格。通过 MPI 评估模型，我们提供了第一个证据，表明预先训练的语言模型中存在人格。我们进一步设计了 Chain Prompting 方法，以可控的方式诱导语言模型具有特定的人格，能够产生多样化的行为。希望通过采用人格作为下游任务的基本心理指导，建立更像人类且在位置对话代理商。