<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vishnyakov-gaintseva-2026-sv">
    <titleInfo>
        <title>SV-Detect: AI-generated Text Detection with Steering Vectors</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mikhail</namePart>
        <namePart type="family">Vishnyakov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tatiana</namePart>
        <namePart type="family">Gaintseva</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>Detecting AI-generated text is especially difficult under distribution shift, such as transfer across domains, source models, and editing attacks. We propose an AI-generated text detector based on steering vectors extracted from the hidden representations of a frozen language model. At each layer, we construct a direction that separates human-written from AI-generated text, and represent each input by its layer-wise alignment with these directions. A lightweight classifier trained on these projection features yields the final detection score. Our method achieves strong performance both in-distribution and under distribution shift, including across domains, source models, and machine-editing transformations such as polishing and rewriting. Interpretation analyses show that the learned directions align with recognizable stylistic cues while capturing substantial additional signal beyond surface features. These results position AI-generated text detection as a representation-space probing problem and show that steering vectors provide a simple and effective solution.</abstract>
    <identifier type="citekey">vishnyakov-gaintseva-2026-sv</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2161/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>49160</start>
            <end>49186</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SV-Detect: AI-generated Text Detection with Steering Vectors
%A Vishnyakov, Mikhail
%A Gaintseva, Tatiana
%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 vishnyakov-gaintseva-2026-sv
%X Detecting AI-generated text is especially difficult under distribution shift, such as transfer across domains, source models, and editing attacks. We propose an AI-generated text detector based on steering vectors extracted from the hidden representations of a frozen language model. At each layer, we construct a direction that separates human-written from AI-generated text, and represent each input by its layer-wise alignment with these directions. A lightweight classifier trained on these projection features yields the final detection score. Our method achieves strong performance both in-distribution and under distribution shift, including across domains, source models, and machine-editing transformations such as polishing and rewriting. Interpretation analyses show that the learned directions align with recognizable stylistic cues while capturing substantial additional signal beyond surface features. These results position AI-generated text detection as a representation-space probing problem and show that steering vectors provide a simple and effective solution.
%U https://aclanthology.org/2026.emnlp-main.2161/
%P 49160-49186

Markdown (Informal)

[SV-Detect: AI-generated Text Detection with Steering Vectors](https://aclanthology.org/2026.emnlp-main.2161/) (Vishnyakov & Gaintseva, EMNLP 2026)

• SV-Detect: AI-generated Text Detection with Steering Vectors (Vishnyakov & Gaintseva, EMNLP 2026)

ACL

• Mikhail Vishnyakov and Tatiana Gaintseva. 2026. SV-Detect: AI-generated Text Detection with Steering Vectors. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 49160–49186, Budapest, Hungary. Association for Computational Linguistics.