arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.07276cs.AIcs.CLcs.LG
收藏

Steer2Adapt:动态组合转向向量引发LLM高效适应

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs

Pengrui Han, Xueqiang Xu, Keyang Xuan, Peiyang Song, Siru Ouyang, Runchu Tian, Yuqing Jiang, Cheng Qian, Pengcheng Jiang, Jiashuo Sun, Junxia Cui, Ming Zhong, G… 展开作者

Pengrui Han, Xueqiang Xu, Keyang Xuan, Peiyang Song, Siru Ouyang, Runchu Tian, Yuqing Jiang, Cheng Qian, Pengcheng Jiang, Jiashuo Sun, Junxia Cui, Ming Zhong, Ge Liu, Jiawei Han, Jiaxuan You

AI总结:

STEER2ADAPT通过动态组合转向向量实现LLM高效适应,适用于需要多协调能力的复杂任务。

摘要:

激活转向已成为一种有前途的方法,用于高效地将大语言模型(LLMs)适应到下游行为。然而,大多数现有的转向方法依赖于每个任务或概念的一个静态方向,这使得它们在任务变化下缺乏灵活性,并且不足以处理需要多个协调能力的复杂任务。为了解决这一限制,我们提出了STEER2ADAPT,一个轻量级框架,通过组合转向向量而不是从头学习新的向量来适应LLMs。在许多领域(例如推理或安全),任务共享一小组底层概念维度。STEER2ADAPT将这些维度作为可重用的、低维的语义先验子空间来捕捉,并通过动态发现少量示例中的基向量的线性组合来适应新任务。在推理和安全领域中,对9个任务和3个模型的实验展示了STEER2ADAPT的有效性,平均提高了8.2%。广泛的分析进一步表明,STEER2ADAPT是LLMs的一种数据高效、稳定且透明的推理时间适应方法。

英文摘要:

Activation steering has emerged as a promising approach for efficiently adapting large language models (LLMs) to downstream behaviors. However, most existing steering methods rely on a single static direction per task or concept, making them inflexible under task variation and inadequate for complex tasks that require multiple coordinated capabilities. To address this limitation, we propose STEER2ADAPT, a lightweight framework that adapts LLMs by composing steering vectors rather than learning new ones from scratch. In many domains (e.g., reasoning or safety), tasks share a small set of underlying concept dimensions. STEER2ADAPT captures these dimensions as a reusable, low-dimensional semantic prior subspace, and adapts to new tasks by dynamically discovering a linear combination of basis vectors from only a handful of examples. Experiments across 9 tasks and 3 models in both reasoning and safety domains demonstrate the effectiveness of STEER2ADAPT, achieving an average improvement of 8.2%. Extensive analyses further show that STEER2ADAPT is a data-efficient, stable, and transparent inference-time adaptation method for LLMs.

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。

↑