用神经元激活模式统一优化大模型微调，提升效率与知识保留。
Neuron-Guided Fine-Tuning: Unlocking Efficient Alignment Mechanisms for Large Language Models
- 以神经元激活为信号，动态选择关键参数更新。
- 在多个基准上优于主流方法，遗忘问题明显缓解。
- 适合追求高效微调且需保留通用知识的场景。
现有监督微调方法，尤其是全参数微调，常面临参数冗余、数据质量不一和灾难性遗忘等问题，现有方法多孤立应对，缺乏统一优化信号来协调数据筛选、参数更新与知识保留。为此，我们提出神经元引导微调（NGFT），一个利用神经元激活模式作为统一代理的综合性框架。NGFT通过三个协同机制运行：(1) 自适应任务特定神经元选择，在一次前向传播中识别关键神经元，集中更新并减少冗余；(2) 基于激活的数据选择，优先挑选对关键神经元贡献大的信息密集样本；(3) 神经元激活对齐，一种新损失函数，将激活锚定在预训练状态，深化表征学习并保留通用知识。在三种模型上的实验结果表明，NGFT在领域特定与通用基准上均显著优于主流微调方法，在效率与性能上表现更优，同时有效缓解灾难性遗忘。
原文摘要 · Abstract (English)
Existing Supervised Fine-Tuning paradigms, particularly Full Parameter Fine-Tuning are often plagued by parameter redundancy, inconsistent data quality, and catastrophic forgetting, which current methods typically address in isolation and lack a unified optimization signal to bridge data selection, parameter updates, and knowledge preservation. To address this, we propose Neuron-Guided Fine-Tuning (NGFT), a holistic framework that leverages neuron activation patterns as a universal proxy to unify the fine-tuning lifecycle. NGFT operates via three synergistic mechanisms: (1) Adaptive Task-Specific Neuron Selection, which identifies essential neurons in a single forward pass to concentrate updates and reduce redundancy; (2) Activation-Based Data Selection, which prioritizes information-dense samples that maximize contribution to key neurons; and (3) Neuron Activation Alignment, a novel loss function that anchors activations to pre-trained states, deepening representation learning and preserving general knowledge. Experimental results across three models across both domain-specific and general benchmarks demonstrate that NGFT significantly outperforms existing mainstream fine-tuning methods in both efficiency and performance, while effectively mitigating catastrophic forgetting.
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。