LLM one-shot style transfer for Authorship Attribution and Verification Article Swipe

MAKE IMPACT

Pablo Miralles-González , Javier Huertas‐Tato , Alejandro Martín , David Camacho · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2510.13302

Computational stylometry analyzes writing style through quantitative patterns in text, supporting applications from forensic tasks such as identity linking and plagiarism detection to literary attribution in the humanities. Supervised and contrastive approaches rely on data with spurious correlations and often confuse style with topic. Despite their natural use in AI-generated text detection, the CLM pre-training of modern LLMs has been scarcely leveraged for general authorship problems. We propose a novel unsupervised approach based on this extensive pre-training and the in-context learning capabilities of LLMs, employing the log-probabilities of an LLM to measure style transferability from one text to another. Our method significantly outperforms LLM prompting approaches of comparable scale and achieves higher accuracy than contrastively trained baselines when controlling for topical correlations. Moreover, performance scales fairly consistently with the size of the base model and, in the case of authorship verification, with an additional mechanism that increases test-time computation; enabling flexible trade-offs between computational cost and accuracy.

Type

preprint

Landing Page

http://arxiv.org/abs/2510.13302

PDF

https://arxiv.org/pdf/2510.13302

OA Status

green

OpenAlex ID

https://openalex.org/W4415275674

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4415275674

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2510.13302

Digital Object Identifier

Title

LLM one-shot style transfer for Authorship Attribution and Verification

Work title

Type

preprint

OpenAlex work type

Publication year

2025

Year of publication

Publication date

2025-10-15

Full publication date if available

Authors

Pablo Miralles-González, Javier Huertas‐Tato, Alejandro Martín, David Camacho

List of authors in order

Landing page

https://arxiv.org/abs/2510.13302

Publisher landing page

PDF URL

https://arxiv.org/pdf/2510.13302

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2510.13302

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload