SOURCE-LINKED INTELLIGENCE

Minimally Invasive Steering of Language Models

arXiv · AI, language, vision and robotics · article · Sep 24, 2026 · UTC

Pre-logit steering adapts a frozen language model to a test-time reward by adding vectors to its final hidden states. Unregularized reward optimization can substantially alter the output distribution and degrade generation quality. We propose Minimally Invasive Steering Vector Optimization (MISVO), which penalizes interventions using the local KL geometry of the induced token distribution. The resulting Fisher quadratic measures distributional sensitivity and admits an analytic gradient computed through matrix--vector products with the frozen language-model head. We derive an exact decompositi

Read original source ↗ Open in workspace

recordType

paper

region

Global