<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ren-etal-2026-style">
    <titleInfo>
        <title>Style-Ruler: Inference-Only Stylized Translation via Unsupervised Extraction and Agentic Collaboration</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hong</namePart>
        <namePart type="family">Ren</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiahe</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shaolin</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Deyi</namePart>
        <namePart type="family">Xiong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nannan</namePart>
        <namePart type="family">Wu</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>While Large Language Models have achieved state-of-the-art performance in general machine translation, they frequently struggle to adhere to complex stylistic nuances and lexical constraints strictly and often revert to a neutral style. The scarcity of style-specific parallel data hinders existing solutions, whereas standard prompting lacks rigorous verification mechanisms. To bridge this gap, we propose Style-Ruler, an inference-only agentic framework that operationalizes style via unsupervised extraction and neuro-symbolic verification. Style-Ruler orchestrates three specialized agents: (1) a Style-Reverse Analyst (SRA) that mines quantifiable linguistic constraints from monolingual reference texts via unsupervised extraction; (2) a Constraint-Adaptive Translator (CAT) that employs a Style-Chain-of-Thought mechanism to plan stylistic adherence before generation explicitly; and (3) a Sandbox-Augmented Auditor (SAA) that provides heterogeneous feedback through deterministic code execution. These components form a closed-loop refinement mechanism where symbolic logic guides neural generation. Extensive experiments on the GuoFeng Webnovel dataset and WMT24++ benchmark demonstrate the superiority of our approach. Style-Ruler achieves a CSR of 82.4% on stylized translation, surpassing standard Chain-of-Thought prompting by over 50%, while improving BLEU scores by +1.0 on En࢐Zh.</abstract>
    <identifier type="citekey">ren-etal-2026-style</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.811/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>17178</start>
            <end>17195</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Style-Ruler: Inference-Only Stylized Translation via Unsupervised Extraction and Agentic Collaboration
%A Ren, Hong
%A Li, Jiahe
%A Zhu, Shaolin
%A Xiong, Deyi
%A Wu, Nannan
%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 ren-etal-2026-style
%X While Large Language Models have achieved state-of-the-art performance in general machine translation, they frequently struggle to adhere to complex stylistic nuances and lexical constraints strictly and often revert to a neutral style. The scarcity of style-specific parallel data hinders existing solutions, whereas standard prompting lacks rigorous verification mechanisms. To bridge this gap, we propose Style-Ruler, an inference-only agentic framework that operationalizes style via unsupervised extraction and neuro-symbolic verification. Style-Ruler orchestrates three specialized agents: (1) a Style-Reverse Analyst (SRA) that mines quantifiable linguistic constraints from monolingual reference texts via unsupervised extraction; (2) a Constraint-Adaptive Translator (CAT) that employs a Style-Chain-of-Thought mechanism to plan stylistic adherence before generation explicitly; and (3) a Sandbox-Augmented Auditor (SAA) that provides heterogeneous feedback through deterministic code execution. These components form a closed-loop refinement mechanism where symbolic logic guides neural generation. Extensive experiments on the GuoFeng Webnovel dataset and WMT24++ benchmark demonstrate the superiority of our approach. Style-Ruler achieves a CSR of 82.4% on stylized translation, surpassing standard Chain-of-Thought prompting by over 50%, while improving BLEU scores by +1.0 on En࢐Zh.
%U https://aclanthology.org/2026.findings-emnlp.811/
%P 17178-17195

Markdown (Informal)

[Style-Ruler: Inference-Only Stylized Translation via Unsupervised Extraction and Agentic Collaboration](https://aclanthology.org/2026.findings-emnlp.811/) (Ren et al., Findings 2026)

• Style-Ruler: Inference-Only Stylized Translation via Unsupervised Extraction and Agentic Collaboration (Ren et al., Findings 2026)

ACL

• Hong Ren, Jiahe Li, Shaolin Zhu, Deyi Xiong, and Nannan Wu. 2026. Style-Ruler: Inference-Only Stylized Translation via Unsupervised Extraction and Agentic Collaboration. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 17178–17195, Budapest, Hungary. Association for Computational Linguistics.