Dynamic Generation of Personalities with Large Language Models

In the realm of mimicking human deliberation, large language models (LLMs)show promising performance, thereby amplifying the importance of this researcharea. Deliberation is influenced by both logic and personality. However,previous studies predominantly focused on the logic of LLMs, neglecting theexploration of personality aspects. In this work, we introduce DynamicPersonality Generation (DPG), a dynamic personality generation method based onHypernetworks. Initially, we embed the Big Five personality theory into GPT-4to form a personality assessment machine, enabling it to evaluate characters'personality traits from dialogues automatically. We propose a new metric toassess personality generation capability based on this evaluation method. Then,we use this personality assessment machine to evaluate dialogues in scriptdata, resulting in a personality-dialogue dataset. Finally, we fine-tune DPG onthe personality-dialogue dataset. Experiments prove that DPG's personalitygeneration capability is stronger after fine-tuning on this dataset thantraditional fine-tuning methods, surpassing prompt-based GPT-4.