Due to the limited computational resources, most Large Language Models (LLMs) developers can only fine-tune Small Language Models (SLMs) on their own data. These private SLMs typically have limited effectiveness. To boost the performance of private SLMs, this paper proposes to ask general LLMs for help. The general LLMs can be APIs or larger LLMs whose inference cost the developers can afford. Specifically, we propose the G-Boost framework where a private SLM adaptively performs collaborative inference with a general LLM under the guide of process reward. Experiments demonstrate that our framework can significantly boost the performance of private SLMs.

翻译：由于计算资源有限，大多数大语言模型开发者仅能在自有数据上微调小语言模型。这类私有小语言模型通常性能有限。为提升私有小语言模型的性能，本文提出向通用大语言模型寻求协助。通用大语言模型可以是API接口或开发者能够承担推理成本的更大规模模型。具体而言，我们提出G-Boost框架，使私有小语言模型在过程奖励的引导下与通用大语言模型进行自适应协同推理。实验表明，该框架能显著提升私有小语言模型的性能。