<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-bhattacharjee-2026-author">
    <titleInfo>
        <title>Author-Stigmatising Hazards in LLM-Generated Literary Translation: Evaluation and Mitigation through Danmei-EPV</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yin</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Deblina</namePart>
        <namePart type="family">Bhattacharjee</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>As LLM translation becomes a common way for English-language readers to read non- Western literature, a class of harm emerges for which NLP currently lacks vocabulary: the source author can be stigmatised through accumulated translation choices that are not detected by standard MT metrics. Humanities scholarship documents this process for Chinese danmei author Mo Xiang Tong Xiu (MXTX), whose novels and fan-translated public statements circulate widely in Anglophone fandom. Under China’s censorship of queer content, MXTX writes pseudonymously and hedges her public statements (Hu et al., 2024). Anglophone anti-fans read this caution as suspicious evasion rather than a survival strategy (Ng, 2024; Springman, 2024). We ask whether LLM-based translations reproduce the translation choices underlying this stigmatisation, operationalising three measurable hazards: voice collapse, connotation flattening, and hedging erasure. We introduce DANMEI-EPV, a 412- item benchmark double-annotated by professional literary translators, and evaluate eight LLMs in four prompting conditions against a 2,000-sentence GuoFeng-Webnovel reference. Every model exhibits all hazards at non-trivial rates, 5 to 6× higher than the GuoFeng reference. Further, newer high-capacity models optimised for fluent English flatten connotation more than smaller older models, suggesting that optimising for English fluency can trade off against source rhetoricity (Spivak, 1993). Finally, a lightweight inference-time intervention, “rhetorical-silence prompting”, reduces voice collapse by 27.4% and connotation flattening by 19.6% without retraining.</abstract>
    <identifier type="citekey">zhang-bhattacharjee-2026-author</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.512/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>10715</start>
            <end>10733</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Author-Stigmatising Hazards in LLM-Generated Literary Translation: Evaluation and Mitigation through Danmei-EPV
%A Zhang, Yin
%A Bhattacharjee, Deblina
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F zhang-bhattacharjee-2026-author
%X As LLM translation becomes a common way for English-language readers to read non- Western literature, a class of harm emerges for which NLP currently lacks vocabulary: the source author can be stigmatised through accumulated translation choices that are not detected by standard MT metrics. Humanities scholarship documents this process for Chinese danmei author Mo Xiang Tong Xiu (MXTX), whose novels and fan-translated public statements circulate widely in Anglophone fandom. Under China’s censorship of queer content, MXTX writes pseudonymously and hedges her public statements (Hu et al., 2024). Anglophone anti-fans read this caution as suspicious evasion rather than a survival strategy (Ng, 2024; Springman, 2024). We ask whether LLM-based translations reproduce the translation choices underlying this stigmatisation, operationalising three measurable hazards: voice collapse, connotation flattening, and hedging erasure. We introduce DANMEI-EPV, a 412- item benchmark double-annotated by professional literary translators, and evaluate eight LLMs in four prompting conditions against a 2,000-sentence GuoFeng-Webnovel reference. Every model exhibits all hazards at non-trivial rates, 5 to 6× higher than the GuoFeng reference. Further, newer high-capacity models optimised for fluent English flatten connotation more than smaller older models, suggesting that optimising for English fluency can trade off against source rhetoricity (Spivak, 1993). Finally, a lightweight inference-time intervention, “rhetorical-silence prompting”, reduces voice collapse by 27.4% and connotation flattening by 19.6% without retraining.
%U https://aclanthology.org/2026.findings-emnlp.512/
%P 10715-10733

Markdown (Informal)

[Author-Stigmatising Hazards in LLM-Generated Literary Translation: Evaluation and Mitigation through Danmei-EPV](https://aclanthology.org/2026.findings-emnlp.512/) (Zhang & Bhattacharjee, Findings 2026)

• Author-Stigmatising Hazards in LLM-Generated Literary Translation: Evaluation and Mitigation through Danmei-EPV (Zhang & Bhattacharjee, Findings 2026)

ACL

• Yin Zhang and Deblina Bhattacharjee. 2026. Author-Stigmatising Hazards in LLM-Generated Literary Translation: Evaluation and Mitigation through Danmei-EPV. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 10715–10733, Budapest, Hungary. Association for Computational Linguistics.