arXiv cs.AI· Zhangming Li, Qinghao Hu, Weifan Guan, Yifan Zhang, Peisong Wang, Jian Cheng·· 13 小时前AI 评分31
NormTune：面向推理密集型任务的范数引导参数高效微调方法
NormTune: Norm-Guided Parameter-Efficient Fine-Tuning for Reasoning-Intensive Tasks
AI 导读
研究者提出 NormTune，一种按权重更新范数自适应增强更新不足层的参数高效微调策略，用于缩小 PEFT 与全量微调在推理密集型任务上的差距。
正文 · 原文
Abstract:Full fine-tuning has achieved remarkable success on reasoning-intensive tasks, but it often requires substantial GPU resource consumption. Parameter-efficient fine-tuning (PEFT) provides a promising alternative for reducing this cost, yet we observe a substantial performance gap on reasoning-intensive tasks. In this paper, we present three key observations showing that this gap is closely associated with norm-related under-adaptation, where PEFT produces markedly smaller weight-update norms than full fine-tuning. Based on these observations, we propose Norm-Guided Parameter-Efficient Fine-Tuning (NormTune), a simple yet effective strategy that adaptively strengthens insufficiently updated layers according to their weight-update norms. Extensive experiments show that NormTune consistently enhances multiple PEFT methods across challenging reasoning benchmarks. Specifically, when trained on S1K-1.1, integrating NormTune into rank-8 LoRA, Bone, and MoRA yields substantial average accuracy improvements of 24.24\%, 11.33\%, and 16.21\% , respectively, across AIME 2024, MATH 500, GPQA, and AIME 2025. Moreover, NormTune-enhanced rank-256 LoRA, Bone, and MoRA achieve performance comparable to S1 full fine-tuning, with respective average gains of 2.17\%, 0.93\%, and 3.00\% over this baseline.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.29134 [cs.AI] |
| (or arXiv:2610.29134v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29134 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Li Zhangming [view email]
[v1]
Wed, 21 Oct 2026 03:14:09 UTC (2,229 KB)
来源：arXiv cs.AI · arxiv.org