Editing Personality for Large Language Models

arXiv:2310.02168v3 Announce Type: replace-cross
Abstract: 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 a new benchmark dataset PersonalityEdit to address this task. Drawing on the theory in Social Psychology, we isolate three representative traits, namely Neuroticism, …

arxiv cs.ai cs.cl cs.cy cs.lg cs.ma editing language language models large language large language models personality type