arXiv 2602.044282026-02-04cs.CL

细粒度激活引导：引导更少，实现更多

Fine-Grained Activation Steering: Steering Less, Achieving More

School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore（电子与电气工程学院，南洋理工大学，新加坡）；Home Team Science and Technology Agency (HTX), Singapore（家庭团队科技局（HTX），新加坡）

Zijian Feng, Tianjiao Li, Zixiao Zhu, Hanzhang Zhou, Junlang Qian, Li Zhang, Jia Jim Deryl Chua, Lee Onn Mak, Gee Wah Ng, Kezhi Mao

备注：: ICLR 2026

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

AUSteer通过细粒度激活引导方法，精准干预有益激活单元，提升LLM行为调整的效率与效果。

摘要：

激活引导已成为一种成本效益高的方法，用于修改大型语言模型（LLM）的行为。现有方法通常在块级别进行干预，引导选定的注意力头、前馈网络或残差流的捆绑激活。然而，我们发现块级别的激活本质上是异质的，混杂了有益的、无关的和有害的特征，从而使得块级别引导粗略、低效且侵入性。为了探讨根本原因，我们将块激活分解为细粒度的原子单元（AU）级别激活，其中每个AU级别激活对应块激活的一个维度，每个AU表示块权重矩阵的一个切片。引导AU级别激活相当于引导其关联的AU。我们的理论和实证分析表明，异质性出现是因为不同的AU或维度控制不同的LLM输出token分布。因此，块级别引导不可避免地同时移动有益和有害的token方向，从而降低效率。限制干预到有益的AU可以产生更精确和有效的引导。基于这一见解，我们提出了AUSteer，一种简单且高效的在AU级别操作的方法。AUSteer首先通过在对比样本上计算激活动量来全局识别判别性的AU。然后，它分配适应性引导强度，以适应多样化的输入和选定的AU激活。在多个LLM和任务上的全面实验表明，AUSteer在引导显著较少的激活的同时，始终优于先进的基线方法，证明了引导更少可以实现更多。

英文摘要：

Activation steering has emerged as a cost-effective paradigm for modifying large language model (LLM) behaviors. Existing methods typically intervene at the block level, steering the bundled activations of selected attention heads, feedforward networks, or residual streams. However, we reveal that block-level activations are inherently heterogeneous, entangling beneficial, irrelevant, and harmful features, thereby rendering block-level steering coarse, inefficient, and intrusive. To investigate the root cause, we decompose block activations into fine-grained atomic unit (AU)-level activations, where each AU-level activation corresponds to a single dimension of the block activation, and each AU denotes a slice of the block weight matrix. Steering an AU-level activation is thus equivalent to steering its associated AU. Our theoretical and empirical analysis show that heterogeneity arises because different AUs or dimensions control distinct token distributions in LLM outputs. Hence, block-level steering inevitably moves helpful and harmful token directions together, which reduces efficiency. Restricting intervention to beneficial AUs yields more precise and effective steering. Building on this insight, we propose AUSteer, a simple and efficient method that operates at a finer granularity of the AU level. AUSteer first identifies discriminative AUs globally by computing activation momenta on contrastive samples. It then assigns adaptive steering strengths tailored to diverse inputs and selected AU activations. Comprehensive experiments on multiple LLMs and tasks show that AUSteer consistently surpasses advanced baselines while steering considerably fewer activations, demonstrating that steering less achieves more.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

AI总结：

摘要：

英文摘要：

相关论文