Can Activation Steering Capture Multidimensional Authorship Style?

2026-09-04

AI Summary

研究通过结构化对比提示在激活空间中构建丰富风格表示，提出无训练框架A3S，解决多维度写作风格控制问题。

Abstract

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 stylistic signal, explaining why naive aggregation fails. We operationalize this in Aspect-Aware Activation Steering (A3S), a training-free framework that merges per-aspect contrastive directions with interference-aware aggregation and tunes steering strength per instance. A3S improves authorship style transfer where it is genuinely multi-aspect, outperforms a trained baseline in preference evaluations on out-of-domain benchmarks, and keeps target-exemplar overlap consistently low.

Problem

• activation steering
• authorship style
• multidimensional

Innovation

• Activation Steering
• Contrastive Prompting
• Authorship Style Transfer
• A3S
• Interference-aware Aggregation