Local Ai
Topological Steering
arXiv:2609.00597v1 Announce Type: new Abstract: With the rapid rise of large language models (LLMs), controlling undesirable model behaviors has become increasingly important. Existing behavioral cont
arXiv:2609.00597v1 Announce Type: new Abstract: 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 diagrams, our method connects activation-based steering with TDA and enables more robust behavioral control. We show that Topological Steering consistently modifies LLM behavior across multiple model families and model sizes.
Related
- Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers
- RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs
- Toward Localizing and Repairing Bias in Transformer Attention Heads
- Adaptively Robust LLM Monitoring via Activation Watermarking
Source: arXiv cs.LG | 2026-09-02