FroM: Frobenius Norm-Based Data-Free Adaptive Model Merging

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Zijian, Feng, Xiaocheng, Liu, Huixin, Huang, Yichong, Liu, Ting, Qin, Bing
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918142808162304
author Li, Zijian
Feng, Xiaocheng
Liu, Huixin
Huang, Yichong
Liu, Ting
Qin, Bing
author_facet Li, Zijian
Feng, Xiaocheng
Liu, Huixin
Huang, Yichong
Liu, Ting
Qin, Bing
contents With the development of large language models, fine-tuning has emerged as an effective method to enhance performance in specific scenarios by injecting domain-specific knowledge. In this context, model merging techniques provide a solution for fusing knowledge from multiple fine-tuning models by combining their parameters. However, traditional methods often encounter task interference when merging full fine-tuning models, and this problem becomes even more evident in parameter-efficient fine-tuning scenarios. In this paper, we introduce an improvement to the RegMean method, which indirectly leverages the training data to approximate the outputs of the linear layers before and after merging. We propose an adaptive merging method called FroM, which directly measures the model parameters using the Frobenius norm, without any training data. By introducing an additional hyperparameter for control, FroM outperforms baseline methods across various fine-tuning scenarios, alleviating the task interference problem.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02478
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FroM: Frobenius Norm-Based Data-Free Adaptive Model Merging
Li, Zijian
Feng, Xiaocheng
Liu, Huixin
Huang, Yichong
Liu, Ting
Qin, Bing
Computation and Language
With the development of large language models, fine-tuning has emerged as an effective method to enhance performance in specific scenarios by injecting domain-specific knowledge. In this context, model merging techniques provide a solution for fusing knowledge from multiple fine-tuning models by combining their parameters. However, traditional methods often encounter task interference when merging full fine-tuning models, and this problem becomes even more evident in parameter-efficient fine-tuning scenarios. In this paper, we introduce an improvement to the RegMean method, which indirectly leverages the training data to approximate the outputs of the linear layers before and after merging. We propose an adaptive merging method called FroM, which directly measures the model parameters using the Frobenius norm, without any training data. By introducing an additional hyperparameter for control, FroM outperforms baseline methods across various fine-tuning scenarios, alleviating the task interference problem.
title FroM: Frobenius Norm-Based Data-Free Adaptive Model Merging
topic Computation and Language
url https://arxiv.org/abs/2506.02478