人格向量：通过模型合并调制大型语言模型的人格
Personality Vector: Modulating Personality of Large Language Models by Model Merging
AI总结：
提出通过模型合并构建人格向量，实现大型语言模型人格的连续调制与多特质组合，无需额外训练且可跨模型迁移。
摘要：
受个性化人工智能系统需求的驱动，人们越来越关注使大型语言模型（LLM）的行为与人类特质（如人格）保持一致。以往在LLM中诱导人格的尝试已显示出有希望的结果，但它们难以捕捉人类特质的连续性和多维性。在这项工作中，我们提出了一种通过模型合并来调制LLM人格的新方法。具体来说，我们通过从针对特定人格特质微调的模型的权重中减去预训练模型的权重来构建人格向量。通过合并人格向量，我们使LLM无需额外训练即可展现出期望的人格特质。大量实验表明，人格向量能够实现对特质强度的连续控制，并支持多种特质的组合。此外，人格向量可迁移到各种下游模型，表明它们编码了可泛化的人格表征。我们的代码可在以下网址获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
