@inproceedings{adi-etal-2026-personalization,
title = "Personalization over Generalization: History-Aware Sentence-Level {AI} Detection in Collaborative Writing",
author = "Adi, Rizky and
Suzuki, Yoshimi and
Fukumoto, Fumiyo",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1282/",
pages = "29217--29235",
ISBN = "979-8-89176-459-0",
abstract = "Sentence-level AI detectors are essential for detecting AI misuse in human-AI collaborative writing. Yet existing approaches still treat all authors identically, ignoring individual writing styles. This is a critical oversight, given that the boundary between human and AI text is inherently author-specific. To address this limitation, we propose PHAS-ID (Personalized History-Aware Sentence-level AI Detector), an approach that introduces personalization to sentence-level detection. By matching target sentences against the author{'}s history of labeled documents, PHAS-ID tailors its predictions based on prior writing behaviors. Furthermore, current synthetic datasets for this task fail to capture realistic collaborative patterns, which we address by introducing GhostFill, a style-aware synthetic dataset generation pipeline. Our experiments demonstrate that PHAS-ID outperforms the previous state-of-the-art (SOTA) across seen-author, unseen-author, cross-domain, and cross-generator settings. Ablation studies confirm that these improvements stem from genuine author-specific personalization rather than the mere addition of context. Our source code and dataset are available at our GitHub repository."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adi-etal-2026-personalization">
<titleInfo>
<title>Personalization over Generalization: History-Aware Sentence-Level AI Detection in Collaborative Writing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rizky</namePart>
<namePart type="family">Adi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoshimi</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fumiyo</namePart>
<namePart type="family">Fukumoto</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>Sentence-level AI detectors are essential for detecting AI misuse in human-AI collaborative writing. Yet existing approaches still treat all authors identically, ignoring individual writing styles. This is a critical oversight, given that the boundary between human and AI text is inherently author-specific. To address this limitation, we propose PHAS-ID (Personalized History-Aware Sentence-level AI Detector), an approach that introduces personalization to sentence-level detection. By matching target sentences against the author’s history of labeled documents, PHAS-ID tailors its predictions based on prior writing behaviors. Furthermore, current synthetic datasets for this task fail to capture realistic collaborative patterns, which we address by introducing GhostFill, a style-aware synthetic dataset generation pipeline. Our experiments demonstrate that PHAS-ID outperforms the previous state-of-the-art (SOTA) across seen-author, unseen-author, cross-domain, and cross-generator settings. Ablation studies confirm that these improvements stem from genuine author-specific personalization rather than the mere addition of context. Our source code and dataset are available at our GitHub repository.</abstract>
<identifier type="citekey">adi-etal-2026-personalization</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1282/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>29217</start>
<end>29235</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Personalization over Generalization: History-Aware Sentence-Level AI Detection in Collaborative Writing
%A Adi, Rizky
%A Suzuki, Yoshimi
%A Fukumoto, Fumiyo
%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 adi-etal-2026-personalization
%X Sentence-level AI detectors are essential for detecting AI misuse in human-AI collaborative writing. Yet existing approaches still treat all authors identically, ignoring individual writing styles. This is a critical oversight, given that the boundary between human and AI text is inherently author-specific. To address this limitation, we propose PHAS-ID (Personalized History-Aware Sentence-level AI Detector), an approach that introduces personalization to sentence-level detection. By matching target sentences against the author’s history of labeled documents, PHAS-ID tailors its predictions based on prior writing behaviors. Furthermore, current synthetic datasets for this task fail to capture realistic collaborative patterns, which we address by introducing GhostFill, a style-aware synthetic dataset generation pipeline. Our experiments demonstrate that PHAS-ID outperforms the previous state-of-the-art (SOTA) across seen-author, unseen-author, cross-domain, and cross-generator settings. Ablation studies confirm that these improvements stem from genuine author-specific personalization rather than the mere addition of context. Our source code and dataset are available at our GitHub repository.
%U https://aclanthology.org/2026.emnlp-main.1282/
%P 29217-29235
Markdown (Informal)
[Personalization over Generalization: History-Aware Sentence-Level AI Detection in Collaborative Writing](https://aclanthology.org/2026.emnlp-main.1282/) (Adi et al., EMNLP 2026)
ACL