The Cylindrical Representation Hypothesis for Language Model Steering 事件

The Cylindrical Representation Hypothesis for Language Model Steering arXiv:2605.01844v2 Announce Type: replace Abstract: Steering is a widely used technique for controlling large language models, yet its effects are often unstable and hard to predict. Existing theoretical accounts are largely based on the Linear Representation Hypothesis (LRH). While LRH assumes that concepts can be orthogonalized for lossless control, this idealized mapping fails in real representations and cannot account for