Research2026-05-07
Steer Like the LLM: Activation Steering that Mimics Prompting
Source: Arxiv CS.AI
arXiv:2605.03907v1 Announce Type: cross Abstract: Large language models can be steered at inference time through prompting or activation interventions, but activation steering methods often underperform compared to prompt-based approaches. We propose a framework that formulates prompt steering as a...
arxivpapersprompting