Reason in Style: Discovering and Controlling Style in Language Models

Excerpt

arXiv:2610.00724v1 Announce Type: cross Abstract: Language models learn content and style jointly, making stylistic variation in their outputs difficult to identify and control. We study whether recurring styles in model responses can be discovered without supervision and explicitly controlled. We design an algorithm that learns to separate representations of content and style from language models' outputs and validate its effectiveness on math questions in a controlled setting. By applying this