无需训练即可合并多个专用大模型，实现多任务统一能力。
Training-free LLM Merging for Multi-task Learning
- 通过分层迭代剪枝与缩放，缓解参数冲突问题。
- 在中英文多项选择题上表现优于现有合并方法。
- 适合需要快速集成多任务模型的研究者和开发者。
大型语言模型（LLMs）在多种自然语言处理任务中表现出色。开源模型如LLaMA和Qwen的发布，催生了大量针对特定任务和语言微调的模型。本文探讨一个重要问题：能否将这些专用模型合并为一个具备多任务能力的统一模型？为此，我们提出无需训练的分层迭代合并（Hi-Merging）方法，通过模型级和层级的剪枝与缩放，并基于贡献分析引导，缓解参数冲突。在中英文多项选择与问答任务上的大量实验验证了该方法在多任务学习中的有效性。结果表明，Hi-Merging在多数场景下持续优于现有合并技术，且性能超过在合并数据集上微调的模型。代码已公开于：https://github.com/Applied-Machine-Learning-Lab/Hi-Merging。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse natural language processing (NLP) tasks. The release of open-source LLMs like LLaMA and Qwen has triggered the development of numerous fine-tuned models tailored for various tasks and languages. In this paper, we explore an important question: is it possible to combine these specialized models to create a unified model with multi-task capabilities. We introduces Hierarchical Iterative Merging (Hi-Merging), a training-free method for unifying different specialized LLMs into a single model. Specifically, Hi-Merging employs model-wise and layer-wise pruning and scaling, guided by contribution analysis, to mitigate parameter conflicts. Extensive experiments on multiple-choice and question-answering tasks in both Chinese and English validate Hi-Merging's ability for multi-task learning. The results demonstrate that Hi-Merging consistently outperforms existing merging techniques and surpasses the performance of models fine-tuned on combined datasets in most scenarios. Code is available at: https://github.com/Applied-Machine-Learning-Lab/Hi-Merging.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。