This work develops a self-contained methodology for learning parameter-efficient rotational transformations based on Riemannian optimization and empirically validate the proposed rotation-based steering scheme, demonstrating its superiority in intervention efficiency.
Abstract
Activation steering has emerged as a lightweight approach for controlling model refusal at inference time. A growing line of research explores trainable rotations of activations to develop geometrically principled intervention mechanisms. However, existing techniques rely on auxiliary constructs, such as refusal vectors, to define these rotations. In our work, we develop a self-contained methodology for learning parameter-efficient rotational transformations based on Riemannian optimization. We empirically validate the proposed scheme, demonstrating its superiority in intervention efficiency. An extensive ablation study highlights the importance of key design choices in our method. Our results identify the proposed rotation-based steering scheme as a promising direction for more reliable control over the behavior of LLMs.
Steering Vector Dissection is proposed, a framework to explicitly isolate individual and semantically consistent features from these composite directions that tend to entangle multiple semantic and stylistic concepts into a single composite direction, leading to unpredictable steering effects.
Takeru Hiramatsu, Kyohei Atarashi, Koh Takeuchi et al.· 2 citations
In many teleoperation applications, collecting a large number of demonstrations as required for traditional probabilistic learning from demonstration (LfD) approaches may not be feasible. To still give operators the ability to intuitively create trajectories as Virtual Fixtures (VFs), we propose to leverage a motion pr...
Maximilian Mühlbauer, Marcella Piacentino, R. Mancino et al.· 0 citations
Dexterous twisting is a fundamental yet challenging capability for anthropomorphic manipulation due to its high-dimensional action space, strong spatio-temporal coupling, and complex contact dynamics. While reinforcement learning (RL) often struggles with convergence under such conditions, learning from demonstration (...
Yan-Bin Feng, He Li, Fu-Zhang Han et al.· 2026 IEEE 22nd International...· 0 citations
Dexterous manipulation poses a challenging high-dimensional optimization problem, as useful behaviors require coordinated motion across many hand joints. In reinforcement learning (RL) and sampling-based trajectory optimization, exploration commonly relies on independent robot joint perturbations, making coordinated be...
Harsh Gupta, T. Lum, Chang-Hao Wang et al.· 0 citations
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 u...
Mohammad Mahdi Abootorabi, Armin Saghafian, Ali Bazshoushtari et al.· 0 citations
Activation steering exploits interpretable directions in the residual stream to enable inference-time manipulation of model behavior. Composing steering vectors to apply multiple target behaviors simultaneously is important in various fields-including AI alignment and safety-but remains a challenge for existing activat...
Sri Pranav Kunda, Alexander Kurz, T. Dominik et al.· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduAug 27, 2026
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
