<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-contrast">
    <titleInfo>
        <title>Contrast Comes at a Cost: Prompting Large Language Models for Perception-Centered Gendered Style Transfer</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hongyu</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Neele</namePart>
        <namePart type="family">Falk</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Michael</namePart>
        <namePart type="family">Roth</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Agnieszka</namePart>
        <namePart type="family">Falenska</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Gendered style transfer aims to rewrite text toward linguistic styles commonly associated with feminine or masculine language use while preserving the original meaning. Prior work commonly operationalizes the transferred target style through binary author identity labels, conflating who writes a text with how gender expression is conveyed stylistically in the text itself. In contrast, we focus on perceived gendered style: the qualities attributed to a text by readers, independently of the author’s identity. We study this as a controlled contrastive rewriting problem: given the same source text, can different prompt-based operationalizations induce feminine- and masculine-targeted rewrites, and at what semantic cost? We compare four operationalizations across instruction-tuned LLMs: author identity, gendered voice, general style descriptions, and fine-grained sociolinguistically grounded style instructions, and evaluate them against human-written rewrites. Using automatic metrics, statistical tests, and human evaluation, we find that LLM-generated rewrites often show stronger contrast and higher meaning preservation than human-written ones. Moreover, prompt operationalization systematically shapes the trade-off between perceived stylistic contrast and semantic fidelity. These findings provide practical guidance for prompt design in gendered style transfer and suggest that targeting perceived style with LLMs can yield clearer linguistic signals than relying solely on author-identity-based human rewrites.</abstract>
    <identifier type="citekey">chen-etal-2026-contrast</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2477/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>56220</start>
            <end>56258</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Contrast Comes at a Cost: Prompting Large Language Models for Perception-Centered Gendered Style Transfer
%A Chen, Hongyu
%A Falk, Neele
%A Roth, Michael
%A Falenska, Agnieszka
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F chen-etal-2026-contrast
%X Gendered style transfer aims to rewrite text toward linguistic styles commonly associated with feminine or masculine language use while preserving the original meaning. Prior work commonly operationalizes the transferred target style through binary author identity labels, conflating who writes a text with how gender expression is conveyed stylistically in the text itself. In contrast, we focus on perceived gendered style: the qualities attributed to a text by readers, independently of the author’s identity. We study this as a controlled contrastive rewriting problem: given the same source text, can different prompt-based operationalizations induce feminine- and masculine-targeted rewrites, and at what semantic cost? We compare four operationalizations across instruction-tuned LLMs: author identity, gendered voice, general style descriptions, and fine-grained sociolinguistically grounded style instructions, and evaluate them against human-written rewrites. Using automatic metrics, statistical tests, and human evaluation, we find that LLM-generated rewrites often show stronger contrast and higher meaning preservation than human-written ones. Moreover, prompt operationalization systematically shapes the trade-off between perceived stylistic contrast and semantic fidelity. These findings provide practical guidance for prompt design in gendered style transfer and suggest that targeting perceived style with LLMs can yield clearer linguistic signals than relying solely on author-identity-based human rewrites.
%U https://aclanthology.org/2026.emnlp-main.2477/
%P 56220-56258

Markdown (Informal)

[Contrast Comes at a Cost: Prompting Large Language Models for Perception-Centered Gendered Style Transfer](https://aclanthology.org/2026.emnlp-main.2477/) (Chen et al., EMNLP 2026)

• Contrast Comes at a Cost: Prompting Large Language Models for Perception-Centered Gendered Style Transfer (Chen et al., EMNLP 2026)

ACL

• Hongyu Chen, Neele Falk, Michael Roth, and Agnieszka Falenska. 2026. Contrast Comes at a Cost: Prompting Large Language Models for Perception-Centered Gendered Style Transfer. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 56220–56258, Budapest, Hungary. Association for Computational Linguistics.