Angular Steering: Behavior Control via Rotation in Activation Space

NeurIPSSpotlight2025

Authors
Hieu M. Vu, Tan Minh Nguyen
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Controlling specific behaviors in large language models while preserving their general capabilities is a central challenge for safe and reliable artificial intelligence deployment…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

large language model language model control

← All NeurIPS 2025 Spotlight papers · Browse the whole archive