SOURCE-LINKED INTELLIGENCE

Can Activation Steering Capture Multidimensional Authorship Style?

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

Activation steering has shown promise for controlling LLM generation along well-defined attributes, but it remains unclear whether it can handle the multidimensional and hard-to-define nature of authorship style. We ask whether structured contrastive prompting along rhetorically-motivated dimensions can construct rich style representations directly in activation space, bypassing the need for natural language style descriptors or dedicated training. We find that the resulting directions share a common authorship backbone while conflicting on aspect-specific residuals that carry genuine stylisti

Read original source ↗ Open in workspace

recordType

paper

region

Global