Riemannian-Manifold Steering

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

arXiv:2605.24942v2 Announce Type: replace Abstract: Steering a language model - intervening on its internal activations to change downstream behaviour - has recently expanded beyond linear interpolation to nonlinear methods such as angular and kernelized steering, which define intervention transformations without learning an explicit geometry over paths in activation space. Freshly introduced geometry-aware manifold methods do learn such a geometry, but require labelled class centroids...