paper-with-me

홈 › Papers

Measuring Embedding Sensitivity to Authorial Style in French: Comparing Literary Texts with Language Model Rewritings

2026-05-11 · Benjamin Icard, Lila Sainero, Alice Breton, Evangelia Zve, Jean-Gabriel Ganascia arxiv

Large language models (LLMs) can convincingly imitate human writing styles, yet it remains unclear how much stylistic information is encoded in embeddings from any language model and retained after LLM rewriting. We investigate these questions in French, using a controlled literary dataset to quantify the effect of stylistic variation via changes in embedding dispersion. We observe that embeddings reliably capture authorial stylistic features and that these signals persist after rewriting, while also exhibiting LLM-specific patterns. These analytical results offer promising directions for authorship imitation detection in the era of language models.

📄 PDF Abstract BibTeX arXiv:2605.10606

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Embedding Style Beyond Topics: Analyzing Dispersion Effects Across Different Language Models

2025-01-01 · Benjamin Icard, Evangelia Zve, Lila Sainero, Alice Breton 외

This paper analyzes how writing style affects the dispersion of embedding vectors across multiple, state-of-the-art language models. While early transformer models primarily aligned with topic modeling, this study examin…

Sensitivity

Modeling Authorial Style in Urdu Novels Using Character Interaction Graphs and Graph Neural Networks

2025-12-14 · Hassan Mujtaba, Hamza Naveed, Hanzlah Munir arxiv

Authorship analysis has traditionally focused on lexical and stylistic cues within text, while higher-level narrative structure remains underexplored, particularly for low-resource languages such as Urdu. This work propo…

Personalized Image Generation from an Author Writing Style

2025-07-04 · Sagar Gandhi, Vishal Gandhi arxiv

Translating nuanced, textually-defined authorial writing styles into compelling visual representations presents a novel challenge in generative AI. This paper introduces a pipeline that leverages Author Writing Sheets (A…

Personalized Image Generation

A Supervised Learning Approach Towards Profiling the Preservation of Authorial Style in Literary Translations

2014-08-01 · COLING 2014 8 · Gerard Lynch
Machine TranslationText Classification

Unsupervised Text Style Transfer with Content Embeddings

2021-09-01 · RANLP 2021 9 · Keith Carlson, Allen Riddell, Daniel Rockmore

The style transfer task (here style is used in a broad “authorial” sense with many aspects including register, sentence structure, and vocabulary choice) takes text input and rewrites it in a specified target style prese…

Language ModelingLanguage ModellingMachine TranslationSentence+4