大型语言模型 (LLMs) 中的引导和监控激活越来越多地用于安全性和可解释性。早期的工作假设行为是沿着单一线性方向, 编码的，但最近的研究结果表明复杂的行为, 例如拒绝回答有害的查询, 存在于多维子空间中。然而，, 用于提取这些子空间的现有方法在计算上是昂贵的,，这对于产生长推理轨迹的推理模型来说是禁止的。通过采用递归特征机 (RFM) 算法（可以有效地计算）和探测通知初始化,，我们能够在推理 (Qwen 3) 和非推理 (Qwen 2.5) 模型上在秒, 内识别多维拒绝子空间。虽然 RFM 可以实现更快的子空间识别,，但它在消融任务上也表现出了比其替代方案更好的性能。计划进行更多工作以更好地理解通过不同方法找到的子空间之间的关系。如果得到证实，, RFM 可能成为法学硕士现有子空间提取方法的廉价且可扩展的补充。
Steering and monitoring activations in Large Language Models (LLMs) are increasingly used for both safety and interpretability. Early work assumed behaviours are encoded along single linear directions, but recent findings suggest complex behaviours, such as the refusal to answer harmful queries, live in multi-dimensional subspaces. However, existing methods for extracting these subspaces are computationally expensive, which becomes prohibitive on reasoning models who produce long reasoning traces. By adapting the Recursive Feature Machine (RFM) algorithm -- which can be computed efficiently -- with a probe-informed initialization, we are able to identify the multi-dimensional refusal subspace in seconds, on reasoning (Qwen 3) and non-reasoning (Qwen 2.5) models. While RFM allows for faster subspace identification, it also showed better performances on the ablation task than its alternatives. More work is planned to better understand the relations between subspaces found by different methods. If confirmed, RFM could be a cheap and scalable complement to existing subspace-extraction methods in LLMs.
科目: 人工智能 (cs.AI); 机器学习 (cs.LG)
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)