大模型里真藏着人类价值观地图
大模型不是只会背答案——它的内部空间里，竟然真的有一张人类价值观的拓扑地图。研究者用心理学里成熟的「基本价值观理论」当标尺，给 20 种价值观(比如自由、安全、享乐)各造了 2.6 万条测试样本，然后去量模型内部那些「方向盘」向量之间的几何关系。结果发现：用数据分布统计出来的方向盘，它们之间的远近亲疏和心理学理论预测的人类价值观结构高度吻合——自由和刺激挨得近，安全和传统也挨得近。但用行为训练出来的方向盘，虽然控制效果差不多，内部结构却和人类价值观毫无关系。更妙的是，这张地图越准，模型就越会「举一反三」:推高一个价值观，会自动连带推高兼容的、压低对立的。地图的清晰度还随模型变大而变好，但指令微调反而会把它弄糊。它不是你明天能用上的东西，但它暗示了一件事：模型对齐也许不该只盯着行为对错，而该去校准它内部那张价值观地图。
📄 原文摘要(英文)
As large language models (LLMs) are increasingly deployed in alignment-sensitive contexts, activation steering has emerged as a lightweight, inference-time alternative to fine-tuning methods (e.g., RLHF, DPO) for behavioral control. However, existing work typically validates steering on isolated behaviors, leaving it unclear whether steering vectors encode coherent semantic structure or merely exploit behavior-specific shortcuts. We investigate whether the latent geometry of LLM steering vectors reflects theory-specified structure in human values and morality. Using Schwartz's Theory of Basic Human Values as our primary fine-grained framework, we introduce a 26K-sample benchmark covering 20 human values and analyze distribution-driven methods (e.g., CAA, SphericalSteer, ODESteer) and behavior-centric approaches (e.g., COLD-Steer, BiPO) across diverse model families and sizes. We find that distribution-driven methods recover human value topologies aligned with theoretical predictions (Spearman ρ up to 0.51, p < 10^{-13}). In contrast, behavior-centric methods achieve comparable steering performance but show little correlation with the expected value geometry. Geometric fidelity improves with model scale but drops after instruction tuning. Finally, better geometric alignment also leads to more human-consistent transfer across values: steering one value correctly lifts compatible values and suppresses opposing ones. Code and data are available at: https://github.com/DeepRCL/Steering_Geometry.