@inproceedings{gutekunst-etal-2026-impostors,
title = "The Impostors Method as a Statistical Test for Authorship Verification With Large Language Models as Sampling Source for Hard Negatives",
author = "Gutekunst, Klara M. and
Winter, Yaron and
Potthast, Martin",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.164/",
pages = "3473--3499",
ISBN = "979-8-89176-462-0",
abstract = "Authorship verification asks whether two given texts were written by the same author. Since supervised verification methods often generalize poorly across domains, the unsupervised Impostors Method, inspired by police lineups, reduces verification to in-domain authorship attribution. Using one text as a query, it hides the other among a sample of hard negatives and measures how reliably a style similarity function retrieves it at the top rank. Although widely applied in practice, the Impostors Method still suffers when no in-domain impostor documents are available. Resorting instead to sampling from open-domain collections provides much less control over confounding stylistic variables such as genre or register. Moreover, its statistical foundations remain largely unexplored compared with those of police lineups. In this paper, we recast the Impostors Method as a statistical hypothesis test, enabling a principled assessment of evidential strength without training a decision threshold. We further investigate large language models (LLMs) as a controllable source for generating in-domain impostor documents."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gutekunst-etal-2026-impostors">
<titleInfo>
<title>The Impostors Method as a Statistical Test for Authorship Verification With Large Language Models as Sampling Source for Hard Negatives</title>
</titleInfo>
<name type="personal">
<namePart type="given">Klara</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Gutekunst</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaron</namePart>
<namePart type="family">Winter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Potthast</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>Authorship verification asks whether two given texts were written by the same author. Since supervised verification methods often generalize poorly across domains, the unsupervised Impostors Method, inspired by police lineups, reduces verification to in-domain authorship attribution. Using one text as a query, it hides the other among a sample of hard negatives and measures how reliably a style similarity function retrieves it at the top rank. Although widely applied in practice, the Impostors Method still suffers when no in-domain impostor documents are available. Resorting instead to sampling from open-domain collections provides much less control over confounding stylistic variables such as genre or register. Moreover, its statistical foundations remain largely unexplored compared with those of police lineups. In this paper, we recast the Impostors Method as a statistical hypothesis test, enabling a principled assessment of evidential strength without training a decision threshold. We further investigate large language models (LLMs) as a controllable source for generating in-domain impostor documents.</abstract>
<identifier type="citekey">gutekunst-etal-2026-impostors</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.164/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>3473</start>
<end>3499</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Impostors Method as a Statistical Test for Authorship Verification With Large Language Models as Sampling Source for Hard Negatives
%A Gutekunst, Klara M.
%A Winter, Yaron
%A Potthast, Martin
%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 gutekunst-etal-2026-impostors
%X Authorship verification asks whether two given texts were written by the same author. Since supervised verification methods often generalize poorly across domains, the unsupervised Impostors Method, inspired by police lineups, reduces verification to in-domain authorship attribution. Using one text as a query, it hides the other among a sample of hard negatives and measures how reliably a style similarity function retrieves it at the top rank. Although widely applied in practice, the Impostors Method still suffers when no in-domain impostor documents are available. Resorting instead to sampling from open-domain collections provides much less control over confounding stylistic variables such as genre or register. Moreover, its statistical foundations remain largely unexplored compared with those of police lineups. In this paper, we recast the Impostors Method as a statistical hypothesis test, enabling a principled assessment of evidential strength without training a decision threshold. We further investigate large language models (LLMs) as a controllable source for generating in-domain impostor documents.
%U https://aclanthology.org/2026.findings-emnlp.164/
%P 3473-3499
Markdown (Informal)
[The Impostors Method as a Statistical Test for Authorship Verification With Large Language Models as Sampling Source for Hard Negatives](https://aclanthology.org/2026.findings-emnlp.164/) (Gutekunst et al., Findings 2026)
ACL