Metraipolis › archive › dc_93d4e35d70c7

Predicting Steering Vectors and Adapter Weights for Few-Shot Author-Style Transfer — arXiv:2610.03163

Source
arXiv
Original
https://arxiv.org/abs/2610.03163
License (as archived)
CC0-1.0
Archived
2026-10-05T22:50:30.838Z
SHA-256 of the archived text
a08dc2809002940616dd694c2273a7b88247d39f38ee3b35f0626061557ad4a7
Stable URL of this page
https://metraipolis.com/documento/dc_93d4e35d70c7

How to cite

Predicting Steering Vectors and Adapter Weights for Few-Shot Author-Style Transfer — arXiv:2610.03163 — arXiv, https://arxiv.org/abs/2610.03163 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_93d4e35d70c7 (Metraipolis archive dc_93d4e35d70c7, sha256 a08dc2809002940616dd694c2273a7b88247d39f38ee3b35f0626061557ad4a7)
BibTeX
@misc{dc93d4e35d70c7,
  title = {Predicting Steering Vectors and Adapter Weights for Few-Shot Author-Style Transfer — arXiv:2610.03163},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03163},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_93d4e35d70c7; sha256 a08dc2809002940616dd694c2273a7b88247d39f38ee3b35f0626061557ad4a7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03163. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Adapting large language models to an individual author's style from a few examples is challenging, and scientific writing sharpens the difficulty: formal conventions leave little surface variation, and authors write about their own topics, so extracted ``style'' easily entangles with content. We study style-conditioned abstract generation from a few example abstracts per author and propose three methods: (1) contrastive activation steering, (2) a network that predicts steering vectors, and (3) a hypernetwork that predicts LoRA adapters. We find a consistent trade-off between style imitation and output quality: fine-tuning buys most of the available style signal but forfeits fluency, while the hypernetwork achieves the best trade-off on both seen and unseen authors. Our steering operates at author level, contrasting an author's abstracts against style-neutral generations for the same content. This holds topic fixed, removes the need for a predefined style inventory, and outperforms inventory-based steering. % [EDIT 1a] softened "no single optimal axis" claim Moreover, our analyses demonstrate that manually extracted and predicted steering vectors are near-orthogonal yet score comparably, indicating that style conditioning here can admit at least two unrelated directions rather than requiring one particular axis.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.03163 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-05T22:45:55.837Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).