实现灵活的多LLM集成，助力可扩展知识聚合

Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation

May 28, 2025

作者: Zhenglun Kong, Zheng Zhan, Shiyue Hou, Yifan Gong, Xin Meng, Pengwei Sui, Peiyan Dong, Xuan Shen, Zifeng Wang, Pu Zhao, Hao Tang, Stratis Ioannidis, Yanzhi Wang

cs.AI

摘要

大型语言模型（LLMs）已展现出显著潜力，但通过传统微调持续提升其性能仍面临挑战，尤其是在整合其他专业LLMs能力时。诸如集成和权重融合等流行方法需要大量内存，且难以适应不断变化的数据环境。近期研究尝试将多个LLMs的知识转移至单一目标模型，然而，由于候选模型选择及训练流程的灵活性受限，这些方法普遍存在任务间干扰和性能下降的问题。为解决这些问题，我们提出了一种框架，能够自适应地选择并聚合来自不同LLMs的知识，构建一个更强大的单一模型，从而避免集成方法的高内存开销和权重融合的僵化性。具体而言，我们设计了一个自适应选择网络，根据评分识别最相关的源LLMs，从而减少知识干扰。此外，我们提出了一种动态加权融合策略，该策略考虑了候选LLMs的固有优势，并引入了一种反馈驱动的损失函数，防止选择器收敛于单一源子集。实验结果表明，与现有方法相比，我们的方法能够实现更稳定、可扩展的知识聚合过程，同时将知识干扰减少高达50%。代码已发布于https://github.com/ZLKong/LLM_Integration。

English

Large language models (LLMs) have shown remarkable promise but remain challenging to continually improve through traditional finetuning, particularly when integrating capabilities from other specialized LLMs. Popular methods like ensemble and weight merging require substantial memory and struggle to adapt to changing data environments. Recent efforts have transferred knowledge from multiple LLMs into a single target model; however, they suffer from interference and degraded performance among tasks, largely due to limited flexibility in candidate selection and training pipelines. To address these issues, we propose a framework that adaptively selects and aggregates knowledge from diverse LLMs to build a single, stronger model, avoiding the high memory overhead of ensemble and inflexible weight merging. Specifically, we design an adaptive selection network that identifies the most relevant source LLMs based on their scores, thereby reducing knowledge interference. We further propose a dynamic weighted fusion strategy that accounts for the inherent strengths of candidate LLMs, along with a feedback-driven loss function that prevents the selector from converging on a single subset of sources. Experimental results demonstrate that our method can enable a more stable and scalable knowledge aggregation process while reducing knowledge interference by up to 50% compared to existing approaches. Code is avaliable at https://github.com/ZLKong/LLM_Integration