@inproceedings{li-etal-2026-adaptive,
title = "Adaptive Boundaries: Context-Aware Detection for Synthetic Text",
author = "Li, Haorong and
Ni, Ruitao and
Yang, Haihui and
Gao, Shiping and
Liu, Yang and
Quan, Xiaojun",
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.1649/",
pages = "37479--37498",
ISBN = "979-8-89176-459-0",
abstract = "The widespread adoption of large language models (LLMs) has created an urgent need for accurate and robust detection of AI-generated text. However, existing statistical detectors often rely on a fixed decision boundary, which hinders their ability to generalize across topics, styles, and model variants. In this paper, we propose preference calibration with context-aware thresholding (PC-CAT), a novel framework that integrates preference calibration with context-aware thresholding to improve detection reliability. PC-CAT first applies Simple Preference Optimization (SimPO) to maximize the log-probability gap between paired human-written and AI-generated texts, enhancing discriminability. It then tailors instance-specific thresholds using a lightweight regressor trained with a hybrid centering and ordinal objective. Experiments across diverse domains and generators show that PC-CAT consistently outperforms strong baselines and achieves new state-of-the-art results. Moreover, it exhibits strong robustness under distribution shifts and adversarial attacks. These findings highlight the critical role of adaptive thresholding in advancing the robustness of AI-generated text detectors."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-adaptive">
<titleInfo>
<title>Adaptive Boundaries: Context-Aware Detection for Synthetic Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haorong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruitao</namePart>
<namePart type="family">Ni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haihui</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiping</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Quan</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>The widespread adoption of large language models (LLMs) has created an urgent need for accurate and robust detection of AI-generated text. However, existing statistical detectors often rely on a fixed decision boundary, which hinders their ability to generalize across topics, styles, and model variants. In this paper, we propose preference calibration with context-aware thresholding (PC-CAT), a novel framework that integrates preference calibration with context-aware thresholding to improve detection reliability. PC-CAT first applies Simple Preference Optimization (SimPO) to maximize the log-probability gap between paired human-written and AI-generated texts, enhancing discriminability. It then tailors instance-specific thresholds using a lightweight regressor trained with a hybrid centering and ordinal objective. Experiments across diverse domains and generators show that PC-CAT consistently outperforms strong baselines and achieves new state-of-the-art results. Moreover, it exhibits strong robustness under distribution shifts and adversarial attacks. These findings highlight the critical role of adaptive thresholding in advancing the robustness of AI-generated text detectors.</abstract>
<identifier type="citekey">li-etal-2026-adaptive</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1649/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>37479</start>
<end>37498</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adaptive Boundaries: Context-Aware Detection for Synthetic Text
%A Li, Haorong
%A Ni, Ruitao
%A Yang, Haihui
%A Gao, Shiping
%A Liu, Yang
%A Quan, Xiaojun
%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 li-etal-2026-adaptive
%X The widespread adoption of large language models (LLMs) has created an urgent need for accurate and robust detection of AI-generated text. However, existing statistical detectors often rely on a fixed decision boundary, which hinders their ability to generalize across topics, styles, and model variants. In this paper, we propose preference calibration with context-aware thresholding (PC-CAT), a novel framework that integrates preference calibration with context-aware thresholding to improve detection reliability. PC-CAT first applies Simple Preference Optimization (SimPO) to maximize the log-probability gap between paired human-written and AI-generated texts, enhancing discriminability. It then tailors instance-specific thresholds using a lightweight regressor trained with a hybrid centering and ordinal objective. Experiments across diverse domains and generators show that PC-CAT consistently outperforms strong baselines and achieves new state-of-the-art results. Moreover, it exhibits strong robustness under distribution shifts and adversarial attacks. These findings highlight the critical role of adaptive thresholding in advancing the robustness of AI-generated text detectors.
%U https://aclanthology.org/2026.emnlp-main.1649/
%P 37479-37498
Markdown (Informal)
[Adaptive Boundaries: Context-Aware Detection for Synthetic Text](https://aclanthology.org/2026.emnlp-main.1649/) (Li et al., EMNLP 2026)
ACL
- Haorong Li, Ruitao Ni, Haihui Yang, Shiping Gao, Yang Liu, and Xiaojun Quan. 2026. Adaptive Boundaries: Context-Aware Detection for Synthetic Text. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 37479–37498, Budapest, Hungary. Association for Computational Linguistics.