用动态组合向量让大模型高效适配新任务
Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs
- 通过组合基础向量而非重新学习，实现灵活适配
- 9个任务平均性能提升8.2%，仅需少量样本
- 适合需要快速、透明调整大模型的场景
激活控制已成为高效适配大语言模型（LLMs）以满足下游行为需求的有前景方法。然而，现有方法多依赖每个任务或概念的单一静态方向，面对任务变化时灵活性不足，且难以应对需多种协同能力的复杂任务。为此，我们提出STEER2ADAPT——一种轻量级框架，通过组合已有转向向量而非从头学习新参数来适配模型。在推理阶段，该方法利用少量示例动态发现基础向量的线性组合，捕捉多个任务共有的低维语义先验子空间。在推理与安全两大领域中，针对3个模型的9个任务测试表明，该方法平均性能提升8.2%。大量分析显示，STEER2ADAPT具备数据高效、稳定且可解释的特性，是一种理想的推理时适配方案。
原文摘要 · Abstract (English)
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.
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。