<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="firoozfar-etal-2026-beyond">
    <titleInfo>
        <title>Beyond Surface Forms: A Comprehensive, Mechanism-Oriented Taxonomy of Indirect Linguistic Encoding for LLM-Based Coded Language Detection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hamid</namePart>
        <namePart type="given">Reza</namePart>
        <namePart type="family">Firoozfar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mohammadsadegh</namePart>
        <namePart type="family">Abolhasani</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Reza</namePart>
        <namePart type="family">Mousavi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Paul</namePart>
        <namePart type="given">Jen-Hwa</namePart>
        <namePart type="family">Hu</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>To avoid moderation and surveillance on social media, some users routinely invent indirect linguistic expressions (ILE) that camouflage sensitive meanings. Such disguised expressions surface as algospeak, euphemisms, and adversarial obfuscation, depending on intent and context, and often involve recurring encoding mechanisms. We propose a comprehensive, mechanism-oriented taxonomy of ILE that abstracts away from communicative goals and instead categorizes the underlying operations through which meaning is encoded and recovered. We evaluate the taxonomy by incorporating it into large language model (LLM) prompts and comparing it with four existing taxonomies and a no-taxonomy baseline, using 2,000 manually annotated TikTok and Bluesky posts. The proposed taxonomy attains the strongest document- and span-level performance across three LLMs. Compared with the best-performing benchmark, its document-level gains are +3.8 accuracy/+4.3 macro-F1 percentage points for GPT-5.4, +0.9/+1.3 for Sonnet 4.6, and +2.1/+2.2 for DeepSeek V4. While the direction of improvement is consistent, the magnitude is model-dependent. The span-level gains are mainly driven by higher recall, sometimes at the cost of precision. In an additional cross-lingual evaluation of 800 Chinese coded-language reviews, the unadapted taxonomy also achieves the highest document- and span-level F1 across the three LLMs. The empirical results reveal the importance of a comprehensive, mechanism-oriented taxonomy as a stable scaffold for detecting emerging coded language and a useful input to content moderation.</abstract>
    <identifier type="citekey">firoozfar-etal-2026-beyond</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2444/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>55450</start>
            <end>55473</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Beyond Surface Forms: A Comprehensive, Mechanism-Oriented Taxonomy of Indirect Linguistic Encoding for LLM-Based Coded Language Detection
%A Firoozfar, Hamid Reza
%A Abolhasani, Mohammadsadegh
%A Mousavi, Reza
%A Hu, Paul Jen-Hwa
%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 firoozfar-etal-2026-beyond
%X To avoid moderation and surveillance on social media, some users routinely invent indirect linguistic expressions (ILE) that camouflage sensitive meanings. Such disguised expressions surface as algospeak, euphemisms, and adversarial obfuscation, depending on intent and context, and often involve recurring encoding mechanisms. We propose a comprehensive, mechanism-oriented taxonomy of ILE that abstracts away from communicative goals and instead categorizes the underlying operations through which meaning is encoded and recovered. We evaluate the taxonomy by incorporating it into large language model (LLM) prompts and comparing it with four existing taxonomies and a no-taxonomy baseline, using 2,000 manually annotated TikTok and Bluesky posts. The proposed taxonomy attains the strongest document- and span-level performance across three LLMs. Compared with the best-performing benchmark, its document-level gains are +3.8 accuracy/+4.3 macro-F1 percentage points for GPT-5.4, +0.9/+1.3 for Sonnet 4.6, and +2.1/+2.2 for DeepSeek V4. While the direction of improvement is consistent, the magnitude is model-dependent. The span-level gains are mainly driven by higher recall, sometimes at the cost of precision. In an additional cross-lingual evaluation of 800 Chinese coded-language reviews, the unadapted taxonomy also achieves the highest document- and span-level F1 across the three LLMs. The empirical results reveal the importance of a comprehensive, mechanism-oriented taxonomy as a stable scaffold for detecting emerging coded language and a useful input to content moderation.
%U https://aclanthology.org/2026.emnlp-main.2444/
%P 55450-55473

Markdown (Informal)

[Beyond Surface Forms: A Comprehensive, Mechanism-Oriented Taxonomy of Indirect Linguistic Encoding for LLM-Based Coded Language Detection](https://aclanthology.org/2026.emnlp-main.2444/) (Firoozfar et al., EMNLP 2026)

• Beyond Surface Forms: A Comprehensive, Mechanism-Oriented Taxonomy of Indirect Linguistic Encoding for LLM-Based Coded Language Detection (Firoozfar et al., EMNLP 2026)

ACL

• Hamid Reza Firoozfar, Mohammadsadegh Abolhasani, Reza Mousavi, and Paul Jen-Hwa Hu. 2026. Beyond Surface Forms: A Comprehensive, Mechanism-Oriented Taxonomy of Indirect Linguistic Encoding for LLM-Based Coded Language Detection. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 55450–55473, Budapest, Hungary. Association for Computational Linguistics.