Dynamic Generation of Personalities with Large Language Models
This addresses the need for more human-like AI interactions by focusing on personality aspects, which were previously neglected, though it is incremental as it builds on existing LLM and hypernetwork techniques.
The paper tackles the problem of generating consistent personalities in large language models by introducing Dynamic Personality Generation (DPG), a method based on hypernetworks that fine-tunes on a personality-dialogue dataset, resulting in stronger personality generation capability than traditional fine-tuning methods and surpassing prompt-based GPT-4.
In the realm of mimicking human deliberation, large language models (LLMs) show promising performance, thereby amplifying the importance of this research area. Deliberation is influenced by both logic and personality. However, previous studies predominantly focused on the logic of LLMs, neglecting the exploration of personality aspects. In this work, we introduce Dynamic Personality Generation (DPG), a dynamic personality generation method based on Hypernetworks. Initially, we embed the Big Five personality theory into GPT-4 to form a personality assessment machine, enabling it to evaluate characters' personality traits from dialogues automatically. We propose a new metric to assess personality generation capability based on this evaluation method. Then, we use this personality assessment machine to evaluate dialogues in script data, resulting in a personality-dialogue dataset. Finally, we fine-tune DPG on the personality-dialogue dataset. Experiments prove that DPG's personality generation capability is stronger after fine-tuning on this dataset than traditional fine-tuning methods, surpassing prompt-based GPT-4.