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

• URL: http://arxiv.org/abs/2605.10606v1
• Date: Mon, 11 May 2026 14:05:46 GMT
• Title: Measuring Embedding Sensitivity to Authorial Style in French: Comparing Literary Texts with Language Model Rewritings
• Abstract summary: We find that embeddings reliably capture authorial stylistic features and that these signals persist after rewriting.<n>These results offer promising directions for authorship imitation detection in the era of language models.
• Score: 0.7249400282852115
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• StyleDecipher: Robust and Explainable Detection of LLM-Generated Texts with Stylistic Analysis [18.44456241158174]
  StyleDecipher is a robust and explainable detection framework.<n>It revisits text detection using combined feature extractors to quantify stylistic differences.<n>It consistently achieves state-of-the-art in-domain accuracy.
  arXiv  Detail & Related papers  (2025-10-14T15:07:27Z)
• Better Call Claude: Can LLMs Detect Changes of Writing Style? [5.720553544629197]
  This article explores the zero-shot performance of state-of-the-art large language models (LLMs) on one of the most challenging tasks in authorship analysis.<n> Benchmarking four LLMs on the official PAN2024 and 2025 "Multi-Author Writing Style Analysis" datasets, we present several observations.<n>First, state-of-the-art generative models are sensitive to variations in writing style - even at the granular level of individual sentences.
  arXiv  Detail & Related papers  (2025-08-01T14:49:50Z)
• LINGOLY-TOO: Disentangling Reasoning from Knowledge with Templatised Orthographic Obfuscation [1.2576388595811496]
  We introduce LINGOLY-TOO, a challenging reasoning benchmark grounded in natural language.<n>We permute reasoning problems written in real languages to generate numerous question variations.<n>Experiments and analyses show that models can circumvent reasoning and answer from prior knowledge.
  arXiv  Detail & Related papers  (2025-03-04T19:57:47Z)
• Unnatural Languages Are Not Bugs but Features for LLMs [92.8332103170009]
  Large Language Models (LLMs) have been observed to process non-human-readable text sequences, such as jailbreak prompts.<n>We present a systematic investigation challenging this perception, demonstrating that unnatural languages contain latent features usable by models.
  arXiv  Detail & Related papers  (2025-03-02T12:10:17Z)
• Idiosyncrasies in Large Language Models [54.26923012617675]
  We unveil and study idiosyncrasies in Large Language Models (LLMs)<n>We find that fine-tuning text embedding models on LLM-generated texts yields excellent classification accuracy.<n>We leverage LLM as judges to generate detailed, open-ended descriptions of each model's idiosyncrasies.
  arXiv  Detail & Related papers  (2025-02-17T18:59:02Z)
• Embedding Style Beyond Topics: Analyzing Dispersion Effects Across Different Language Models [0.0699049312989311]
  This study examines the role of writing style in shaping embedding spaces.<n>Using a literary corpus that alternates between topics and styles, we compare the sensitivity of language models across French and English.
  arXiv  Detail & Related papers  (2025-01-01T13:17:16Z)
• Examining Language Modeling Assumptions Using an Annotated Literary Dialect Corpus [0.0]
  We present a dataset of 19th century American literary orthovariant tokens with a novel layer of human-annotated dialect group tags. We find indications that the "dialect effect" produced by intentional orthographic variation employs multiple linguistic channels.
  arXiv  Detail & Related papers  (2024-10-03T16:58:21Z)
• Understanding and Mitigating Language Confusion in LLMs [76.96033035093204]
  We evaluate 15 typologically diverse languages with existing and newly-created English and multilingual prompts.<n>We find that Llama Instruct and Mistral models exhibit high degrees of language confusion.<n>We find that language confusion can be partially mitigated via few-shot prompting, multilingual SFT and preference tuning.
  arXiv  Detail & Related papers  (2024-06-28T17:03:51Z)
• Language models are not naysayers: An analysis of language models on negation benchmarks [58.32362243122714]
  We evaluate the ability of current-generation auto-regressive language models to handle negation. We show that LLMs have several limitations including insensitivity to the presence of negation, an inability to capture the lexical semantics of negation, and a failure to reason under negation.
  arXiv  Detail & Related papers  (2023-06-14T01:16:37Z)
• Learning Interpretable Style Embeddings via Prompting LLMs [46.74488355350601]
  Style representation learning builds content-independent representations of author style in text. Current style representation learning uses neural methods to disentangle style from content to create style vectors. We use prompting to perform stylometry on a large number of texts to create a synthetic dataset and train human-interpretable style representations.
  arXiv  Detail & Related papers  (2023-05-22T04:07:54Z)
• Limits of Detecting Text Generated by Large-Scale Language Models [65.46403462928319]
  Some consider large-scale language models that can generate long and coherent pieces of text as dangerous, since they may be used in misinformation campaigns. Here we formulate large-scale language model output detection as a hypothesis testing problem to classify text as genuine or generated.
  arXiv  Detail & Related papers  (2020-02-09T19:53:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.