English

Mutual Enhancement of Large and Small Language Models with Cross-Silo Knowledge Transfer

Artificial Intelligence 2023-12-12 v1 Computation and Language

Abstract

While large language models (LLMs) are empowered with broad knowledge, their task-specific performance is often suboptimal. It necessitates fine-tuning LLMs with task-specific data, but such data may be inaccessible due to privacy concerns. In this paper, we propose a novel approach to enhance LLMs with smaller language models (SLMs) that are trained on clients using their private task-specific data. To enable mutual enhancement between LLMs and SLMs, we propose CrossLM, where the SLMs promote the LLM to generate task-specific high-quality data, and both the LLM and SLMs are enhanced with the generated data. We evaluate CrossLM using publicly accessible language models across a range of benchmark tasks. The results demonstrate that CrossLM significantly enhances the task-specific performance of SLMs on clients and the LLM on the cloud server simultaneously while preserving the LLM's generalization capability.

Keywords

Cite

@article{arxiv.2312.05842,
  title  = {Mutual Enhancement of Large and Small Language Models with Cross-Silo Knowledge Transfer},
  author = {Yongheng Deng and Ziqing Qiao and Ju Ren and Yang Liu and Yaoxue Zhang},
  journal= {arXiv preprint arXiv:2312.05842},
  year   = {2023}
}