<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arnold-2026-differentially">
    <titleInfo>
        <title>Differentially-Private Text Rewriting reshapes Linguistic Style</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Stefan</namePart>
        <namePart type="family">Arnold</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 Seventh Workshop on Privacy in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ivan</namePart>
            <namePart type="family">Habernal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sepideh</namePart>
            <namePart type="family">Ghanavati</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sara</namePart>
            <namePart type="family">Haghighi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Krithika</namePart>
            <namePart type="family">Ramesh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Timour</namePart>
            <namePart type="family">Igamberdiev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Shomir</namePart>
            <namePart type="family">Wilson</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-397-5</identifier>
    </relatedItem>
    <abstract>Differential Privacy (DP) for text matured from disjointed word-level substitutions to contiguous sentence-level rewriting by leveraging the generative capacity of language models. While this form of text privatization is best suited for balancing formal privacy guarantees with grammatical coherence, its impact on the register identity of text remains largely unexplored. By conducting a multidimensional stylistic profiling of differentially-private rewriting, we demonstrate that the cost of privacy extends far beyond lexical variation. Specifically, we find that rewriting under privacy constraints induces a systematic functional mutation of the text’s communicative signature. This shift is characterized by the severe attrition of interactive markers, contextual references, and complex subordination. By comparing autoregressive paraphrasing against bidirectional substitution across a spectrum of privacy budgets, we observe that both architectures force convergence toward a non-involved and non-persuasive register. This register-blind sanitization effectively preserves semantic content but structurally homogenizes the nuanced stylistic markers that define human-authored discourse.</abstract>
    <identifier type="citekey">arnold-2026-differentially</identifier>
    <identifier type="doi">10.18653/v1/2026.privatenlp-main.7</identifier>
    <location>
        <url>https://aclanthology.org/2026.privatenlp-main.7/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>96</start>
            <end>106</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Differentially-Private Text Rewriting reshapes Linguistic Style
%A Arnold, Stefan
%Y Habernal, Ivan
%Y Ghanavati, Sepideh
%Y Haghighi, Sara
%Y Ramesh, Krithika
%Y Igamberdiev, Timour
%Y Wilson, Shomir
%S Proceedings of the Seventh Workshop on Privacy in Natural Language Processing
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California
%@ 979-8-89176-397-5
%F arnold-2026-differentially
%X Differential Privacy (DP) for text matured from disjointed word-level substitutions to contiguous sentence-level rewriting by leveraging the generative capacity of language models. While this form of text privatization is best suited for balancing formal privacy guarantees with grammatical coherence, its impact on the register identity of text remains largely unexplored. By conducting a multidimensional stylistic profiling of differentially-private rewriting, we demonstrate that the cost of privacy extends far beyond lexical variation. Specifically, we find that rewriting under privacy constraints induces a systematic functional mutation of the text’s communicative signature. This shift is characterized by the severe attrition of interactive markers, contextual references, and complex subordination. By comparing autoregressive paraphrasing against bidirectional substitution across a spectrum of privacy budgets, we observe that both architectures force convergence toward a non-involved and non-persuasive register. This register-blind sanitization effectively preserves semantic content but structurally homogenizes the nuanced stylistic markers that define human-authored discourse.
%R 10.18653/v1/2026.privatenlp-main.7
%U https://aclanthology.org/2026.privatenlp-main.7/
%U https://doi.org/10.18653/v1/2026.privatenlp-main.7
%P 96-106

Markdown (Informal)

[Differentially-Private Text Rewriting reshapes Linguistic Style](https://aclanthology.org/2026.privatenlp-main.7/) (Arnold, PrivateNLP 2026)

• Differentially-Private Text Rewriting reshapes Linguistic Style (Arnold, PrivateNLP 2026)

ACL

• Stefan Arnold. 2026. Differentially-Private Text Rewriting reshapes Linguistic Style. In Proceedings of the Seventh Workshop on Privacy in Natural Language Processing, pages 96–106, San Diego, California. Association for Computational Linguistics.