# Steering Geometry: Validating Human Value Geometry in LLM Steering Space

arXiv: https://arxiv.org/abs/2609.06289 · HTML: https://mlsanity.com/paper/2609.06289/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 5 Sep 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)
- Mechanistic interpretability / [Activation steering methods](https://mlsanity.com/mechinterp/activation-steering-methods/)

## Builds on (most cited first, 25 of 25)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [The Falcon Series of Open Language Models](https://mlsanity.com/paper/2311.16867/) (2023)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization](https://mlsanity.com/paper/2406.00045/) (2024)
- [Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories](https://mlsanity.com/paper/2406.00034/) (2024)
- [Steering Large Language Model Activations in Sparse Spaces](https://mlsanity.com/paper/2503.00177/) (2025)
- [One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs](https://mlsanity.com/paper/2502.18862/) (2025)
- [The Touch'e23-ValueEval Dataset for Identifying Human Values behind Arguments](https://mlsanity.com/paper/2301.13771/) (2023)
- [Spherical Steering: Geometry-Aware Activation Rotation for Language Models](https://mlsanity.com/paper/2602.08169/) (2026)
- [ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment](https://mlsanity.com/paper/2602.17560/) (2026)
- [Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective](https://mlsanity.com/paper/2501.00581/) (2024)
- [COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics](https://mlsanity.com/paper/2603.06495/) (2026)
- [Your Language Model Secretly Contains Personality Subnetworks](https://mlsanity.com/paper/2602.07164/) (2026)
- [VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models](https://mlsanity.com/paper/2602.03160/) (2026)
- [Steering the Herd: A Framework for LLM-based Control of Social Learning](https://mlsanity.com/paper/2504.02648/) (2025)
- [Conditional Optimal Bridge for Riemannian Activation Steering](https://mlsanity.com/paper/2607.10517/) (2026)

## Abstract (arXiv)

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/SteeringGeometry.