<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chintada-etal-2026-orthogonal">
    <titleInfo>
        <title>Orthogonal Style Injection: Mechanistic Persona Steering for Zero-Shot Cross-Lingual Subtitle Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tarun</namePart>
        <namePart type="family">Chintada</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kshetrimayum</namePart>
        <namePart type="given">Boynao</namePart>
        <namePart type="family">Singh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Asif</namePart>
        <namePart type="family">Ekbal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruifeng</namePart>
            <namePart type="family">Xu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ayu</namePart>
            <namePart type="family">Purwarianti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tong</namePart>
            <namePart type="family">Rong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jun</namePart>
            <namePart type="family">Suzuki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hengqin, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-439-2</identifier>
    </relatedItem>
    <abstract>In conversational and cinematic subtitle translation, large language models often exhibit stylistic collapse, defaulting to neutral registers that flatten character-specific personas. Prompt-based attempts to recover style frequently introduce instruction drift and semantic degradation. We propose Orthogonal Style Injection (OSI), a parameter-efficient, inference-time intervention that removes global stylistic bias through orthogonal projection at an intermediate layer and injects a character-specific style vector derived solely from English source dialogue. We evaluate OSI for English-to-Bengali, Hindi, Telugu, Tamil, Kannada, Chinese, Japanese, Spanish, French, German, and Italian subtitle translation, spanning 11 typologically diverse target languages. Results show that zero-shot stylistic transfer depends strongly on pretraining alignment. Llama-3.1-8B yields gains in several European languages but degrades on Indic languages, whereas Qwen-2.5-7B transfers style more robustly across Indic and East Asian languages. To probe sociolinguistic mechanisms, we curate a parallel English-Bengali cinematic dataset as a focused morphological stress test. Automatic metrics and human evaluation show that OSI enables meaningful honorific and register shifts while largely preserving semantic fidelity, revealing a dataset-dependent trade-off between stylistic fidelity and translation quality in highly colloquial, morphologically constrained settings.</abstract>
    <identifier type="citekey">chintada-etal-2026-orthogonal</identifier>
    <location>
        <url>https://aclanthology.org/2026.aacl-long.274/</url>
    </location>
    <part>
        <date>2026-11</date>
        <extent unit="page">
            <start>6058</start>
            <end>6084</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Orthogonal Style Injection: Mechanistic Persona Steering for Zero-Shot Cross-Lingual Subtitle Translation
%A Chintada, Tarun
%A Singh, Kshetrimayum Boynao
%A Ekbal, Asif
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F chintada-etal-2026-orthogonal
%X In conversational and cinematic subtitle translation, large language models often exhibit stylistic collapse, defaulting to neutral registers that flatten character-specific personas. Prompt-based attempts to recover style frequently introduce instruction drift and semantic degradation. We propose Orthogonal Style Injection (OSI), a parameter-efficient, inference-time intervention that removes global stylistic bias through orthogonal projection at an intermediate layer and injects a character-specific style vector derived solely from English source dialogue. We evaluate OSI for English-to-Bengali, Hindi, Telugu, Tamil, Kannada, Chinese, Japanese, Spanish, French, German, and Italian subtitle translation, spanning 11 typologically diverse target languages. Results show that zero-shot stylistic transfer depends strongly on pretraining alignment. Llama-3.1-8B yields gains in several European languages but degrades on Indic languages, whereas Qwen-2.5-7B transfers style more robustly across Indic and East Asian languages. To probe sociolinguistic mechanisms, we curate a parallel English-Bengali cinematic dataset as a focused morphological stress test. Automatic metrics and human evaluation show that OSI enables meaningful honorific and register shifts while largely preserving semantic fidelity, revealing a dataset-dependent trade-off between stylistic fidelity and translation quality in highly colloquial, morphologically constrained settings.
%U https://aclanthology.org/2026.aacl-long.274/
%P 6058-6084

Markdown (Informal)

[Orthogonal Style Injection: Mechanistic Persona Steering for Zero-Shot Cross-Lingual Subtitle Translation](https://aclanthology.org/2026.aacl-long.274/) (Chintada et al., AACL-IJCNLP 2026)

• Orthogonal Style Injection: Mechanistic Persona Steering for Zero-Shot Cross-Lingual Subtitle Translation (Chintada et al., AACL-IJCNLP 2026)

ACL

• Tarun Chintada, Kshetrimayum Boynao Singh, and Asif Ekbal. 2026. Orthogonal Style Injection: Mechanistic Persona Steering for Zero-Shot Cross-Lingual Subtitle Translation. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6058–6084, Hengqin, China. Association for Computational Linguistics.