Personality Vector: Modulating Personality of Large Language Models by Model Merging
This work addresses the demand for personalized AI systems by providing a method to modulate LLM personalities, though it is incremental as it builds on existing fine-tuning and model merging techniques.
The paper tackles the problem of aligning large language models (LLMs) with human personality traits by proposing a model merging method using personality vectors, which enables continuous control over trait intensity and composition without additional training, as shown in experiments demonstrating transferability across models.
Driven by the demand for personalized AI systems, there is growing interest in aligning the behavior of large language models (LLMs) with human traits such as personality. Previous attempts to induce personality in LLMs have shown promising results, but they struggle to capture the continuous and multidimensional nature of human traits. In this work, we propose a novel method for personality modulation in LLMs via model merging. Specifically, we construct personality vectors by subtracting the weights of a pre-trained model from those of the fine-tuned model on a given personality trait. By merging personality vectors, we enable LLMs to exhibit desired personality traits without additional training. Extensive experiments show that personality vectors enable continuous control over trait intensity and support the composition of multiple traits. Furthermore, personality vectors transfer across diverse downstream models, suggesting that they encode generalizable representations of personality. Our code is available at here.