引導幾何：在 LLM 引導空間中驗證人類價值幾何

摘要

當大型語言模型（LLMs）日益部署於對齊敏感的情境中，活化引導已成為行為控制中微調方法（例如 RLHF、DPO）的一種輕量、推論時替代方案。然而，既有研究通常僅在孤立行為上驗證引導，這使得引導向量究竟是編碼了連貫的語意結構，或僅是利用特定行為的捷徑，仍不明確。我們探討 LLM 引導向量的潛在幾何是否反映人類價值與道德中理論所界定的結構。我們以 Schwartz 的基本人類價值理論作為主要細粒度框架，提出一個涵蓋 20 種人類價值的 26K 樣本基準，並分析分佈驅動方法（例如 CAA、SphericalSteer、ODESteer）與行為中心取向（例如 COLD-Steer、BiPO）在多元模型家族與規模上的表現。我們發現，分佈驅動方法能還原與理論預測一致的人類價值拓撲（Spearman ρ 最高達 0.51，p < 10^{-13}）。相較之下，行為中心方法雖達到可比的引導效能，卻與預期的價值幾何幾乎不相關。幾何保真度會隨模型規模提升而改善，但在指令微調後下降。最後，更好的幾何對齊也會帶來更符合人類的跨價值遷移：對某一價值進行引導時，能正確提升相容價值並抑制對立價值。程式碼與資料可於以下網址取得：https://github.com/DeepRCL/Steering_Geometry。

English

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.