arXiv 2510.101572026-01-24cs.CLcs.AI

BILLY：通过合并人设向量来引导大型语言模型进行创造性生成

BILLY: Steering Large Language Models via Merging Persona Vectors for Creative Generation

Department of Electrical Engineering, National Taiwan University（国立台湾大学电子工程系）；Department of Computer Science & Information Engineering, National Taiwan University（国立台湾大学计算机科学与信息工程系）；Graduate Institute of Communication Engineering, National Taiwan University（国立台湾大学通信工程研究所）；CSAIL, Massachusetts Institute of Technology（麻省理工学院计算机科学与人工智能实验室）

Tsung-Min Pai, Jui-I Wang, Li-Chun Lu, Shao-Hua Sun, Hung-Yi Lee, Kai-Wei Chang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

BILLY通过合并人设向量在单个模型中实现多视角生成，提升创造力并降低计算成本。

摘要：

多LLM系统通过模拟人类集体智能来增强大型语言模型的创造力，但存在显著缺点，如计算成本高和推理延迟。为解决这些限制，我们提出了BILLY（BlendIng persona vectors for Large Language model creativitY），一个无需训练的框架，旨在在单个模型中捕捉多LLM协作的好处，即诱导多样化的视角和专业化的专业知识。BILLY通过在模型的激活空间中直接提取和融合多个不同的人设向量来运作。在推理过程中，我们利用这个融合的向量来引导模型的生成过程，使模型能够产生多视角的输出，而无需显式的多LLM通信。我们的实验在以创造力为导向的基准上显示，BILLY超越了单模型提示和传统多LLM方法，同时显著减少了推理时间和计算成本。我们的分析进一步揭示，不同的个人向量可以融合以实现对生成互补方面的有效控制以及更高的可解释性。

英文摘要：

Multi-LLM systems enhance the creativity of large language models by simulating human collective intelligence but suffer from significant drawbacks, such as high computational costs and inference latency. To address these limitations, we propose BILLY (BlendIng persona vectors for Large Language model creativitY), a training-free framework that captures the benefits of multi-LLM collaboration, i.e. inducing diverse perspectives and specialized expertise, within a single model. BILLY operates by extracting and blending multiple distinct persona vectors directly in the model's activation space. We steer the model's generation process with this merged vector while inference, enabling multi-perspective output without explicit multi-LLM communication. Our experiments across creativity-oriented benchmarks demonstrate that BILLY surpasses single model prompting and traditional multi-LLM approaches, while substantially reducing inference time and computational costs. Our analyses further reveal that distinct persona vectors can be blended to achieve both effective control over complementary aspects of generation and greater interpretability.

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。