Steering Geometry: Validating Human Value Geometry in LLM Steering Space
Researchers show LLM activation steering vectors encode human value geometry predicted by Schwartz's theory, with fidelity improving at scale but degrading after instruction tuning.
The study tests whether latent geometry of activation steering vectors reflects theory-specified structure in human values, using Schwartz's Theory of Basic Human Values and a new 26K-sample benchmark spanning 20 values. Distribution-driven methods (CAA, SphericalSteer, ODESteer) recover predicted value topologies with Spearman correlation up to 0.51 (p < 10^-13), while behavior-centric methods (COLD-Steer, BiPO) steer comparably but show little geometric fidelity. Geometric alignment improves with model scale but drops after instruction tuning. Better geometric alignment also yields more human-consistent cross-value transfer, steering one value lifting compatible values and suppressing opposing ones.
- Introduces 26K-sample benchmark covering 20 human values from Schwartz's framework
- Distribution-driven steering methods recover theoretical value geometry (Spearman rho up to 0.51)
- Behavior-centric methods (COLD-Steer, BiPO) steer well but lack geometric fidelity
- Geometric fidelity improves with model scale, drops after instruction tuning
- Aligned geometry yields human-consistent transfer across compatible and opposing values
Full article191 words · extracted from huggingface.co · click to collapse
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.
Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/papers/2609.06289