#activation-control News & Analysis

Riemannian-Manifold Steering: Geometry-Aware Generative Autoencoders for Label-Free Steering

Researchers introduce a Riemannian-manifold framework for steering language models that eliminates the need for labeled data or predefined topologies. The method approximates output-space geometry using a learned encoder trained on concept tokens, enabling more natural intervention trajectories across diverse tasks without per-prompt labeling.