This paper introduces an innovative task focused on editing the personality traits of Large Language Models (LLMs). This task seeks to adjust the models' responses to opinion-related questions on specified topics since an individual's personality often manifests in the form of their expressed opinions, thereby showcasing different personality traits. Specifically, we construct PersonalityEdit, a new benchmark dataset to address this task. Drawing on the theory in Social Psychology, we isolate three representative traits, namely Neuroticism, Extraversion, and Agreeableness, as the foundation for our benchmark. We then gather data using GPT-4, generating responses that align with a specified topic and embody the targeted personality trait. We conduct comprehensive experiments involving various baselines and discuss the representation of personality behavior in LLMs. Our findings uncover potential challenges of the proposed task, illustrating several remaining issues. We anticipate that our work can stimulate further annotation in model editing and personality-related research. Code is available at https://github.com/zjunlp/EasyEdit.
@article{arxiv.2310.02168,
title = {Editing Personality for Large Language Models},
author = {Shengyu Mao and Xiaohan Wang and Mengru Wang and Yong Jiang and Pengjun Xie and Fei Huang and Ningyu Zhang},
journal= {arXiv preprint arXiv:2310.02168},
year = {2024}
}