תגלית סגנון: גילוי ובקרה של סגנון במודלים של שפה

תקציר מקורי באנגליתarXiv: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 method to over 100K verified traces from nine distinct teacher models, we discover six recurring yet imbalanced styles. We then fine-tune smaller student models to follow these styles when explicitly conditioned on them, using importance weighting to balance the contribution of the styles represent