SOURCE-LINKED INTELLIGENCE

Topological Steering

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

With the rapid rise of large language models (LLMs), controlling undesirable model behaviors has become increasingly important. Existing behavioral control methods typically intervene directly in activation or feature space, but such approaches can be sensitive to outliers, distributional shifts, noise, and other local perturbations. Motivated by Topological Data Analysis (TDA), which captures global rather than purely local structure, we propose Topological Steering, a new framework for steering LLM behavior through the topological representation of activation spaces. Using persistence diagra

Read original source ↗ Open in workspace

recordType

paper

region

Global