SOURCE-LINKED INTELLIGENCE

IDEEA: training-free Input-Dependent stEEring via Activation cluster matching

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Steering aligns large language models (LLMs) by injecting a bias into selected activations at inference time, offering a far cheaper alternative to weight-update methods such as supervised fine-tuning or reinforcement learning. However, most existing training-free steering methods are input-independent: a single direction is fitted once and shared across all inputs. This is fundamentally limiting as different inputs occupy different regions of the activation space and admit different optimal steering directions toward the same target concept, much as the gradient with respect to a fixed loss v

Read original source ↗ Open in workspace

recordType

paper

region

Global