@inproceedings{icard-etal-2026-measuring,
title = "Measuring Embedding Sensitivity to Authorial Style in {F}rench: Comparing Literary Texts with Language Model Rewritings",
author = "Icard, Benjamin and
Sainero, Lila and
Breton, Alice and
Zve, Evangelia and
Ganascia, Jean-Gabriel",
editor = {Hamilton, Sil and
{\"O}hman, Emily and
Hicke, Rebecca M. M. and
Bizzoni, Yuri and
Bax, Axel and
Matthews, Jacob A. and
H{\"a}m{\"a}l{\"a}inen, Mika},
booktitle = "Proceedings of the 6th International Conference on Natural Language Processing for the Digital Humanities",
month = jul,
year = "2026",
address = "San Diego, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.nlp4dh-1.8/",
pages = "69--82",
ISBN = "979-8-89176-427-9",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="icard-etal-2026-measuring">
<titleInfo>
<title>Measuring Embedding Sensitivity to Authorial Style in French: Comparing Literary Texts with Language Model Rewritings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Icard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lila</namePart>
<namePart type="family">Sainero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alice</namePart>
<namePart type="family">Breton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evangelia</namePart>
<namePart type="family">Zve</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean-Gabriel</namePart>
<namePart type="family">Ganascia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th International Conference on Natural Language Processing for the Digital Humanities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sil</namePart>
<namePart type="family">Hamilton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="given">M</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Hicke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Axel</namePart>
<namePart type="family">Bax</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacob</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Matthews</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-427-9</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">icard-etal-2026-measuring</identifier>
<location>
<url>https://aclanthology.org/2026.nlp4dh-1.8/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>69</start>
<end>82</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Measuring Embedding Sensitivity to Authorial Style in French: Comparing Literary Texts with Language Model Rewritings
%A Icard, Benjamin
%A Sainero, Lila
%A Breton, Alice
%A Zve, Evangelia
%A Ganascia, Jean-Gabriel
%Y Hamilton, Sil
%Y Öhman, Emily
%Y Hicke, Rebecca M. M.
%Y Bizzoni, Yuri
%Y Bax, Axel
%Y Matthews, Jacob A.
%Y Hämäläinen, Mika
%S Proceedings of the 6th International Conference on Natural Language Processing for the Digital Humanities
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, USA
%@ 979-8-89176-427-9
%F icard-etal-2026-measuring
%X 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.
%U https://aclanthology.org/2026.nlp4dh-1.8/
%P 69-82
Markdown (Informal)
[Measuring Embedding Sensitivity to Authorial Style in French: Comparing Literary Texts with Language Model Rewritings](https://aclanthology.org/2026.nlp4dh-1.8/) (Icard et al., NLP4DH 2026)
ACL