@inproceedings{guo-etal-2026-tokens,
title = "Not All Tokens Are Equal: Syntax-Pattern Weighted Likelihood Difference Joint Detection for Neural-Training-Free {AI}-Generated Text Detection",
author = "Guo, Tianyu and
Hao, Shufeng and
Li, JiaQi and
Shi, Chongyang",
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.1912/",
doi = "10.18653/2026.findings-emnlp.1912",
pages = "40743--40758",
ISBN = "979-8-89176-462-0",
abstract = "Existing neural-training-free AI-Generated Text (AIGT) detectors usually aggregate token-level probability signals with uniform weights. However, this ignores an important linguistic regularity: human-written and AI-generated texts exhibit different Part-Of-Speech (POS) n-gram patterns, making certain tokens more informative than others. To address the limitations, we propose SWLD-Joint (Syntax-pattern Weighted Log-likelihood Difference Joint Detection), a calibration-based neural-training-free detector without gradient-based optimization or neural classifier fine-tuning. SWLD-Joint first estimates POS n-gram template weights from labeled calibration data and then combines them with a POS-trajectory calibration signal to focus on syntactically informative positions. Experiments on DetectRL, RAID, and HC3{\_}Ext show robust gains under domain shift, generator mismatch, and adversarial perturbations. Ablations, parameter analysis, case studies, score distributions, and ROC curves verify the effectiveness of syntax-pattern weighting. Code and data will be released upon acceptance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2026-tokens">
<titleInfo>
<title>Not All Tokens Are Equal: Syntax-Pattern Weighted Likelihood Difference Joint Detection for Neural-Training-Free AI-Generated Text Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tianyu</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shufeng</namePart>
<namePart type="family">Hao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">JiaQi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chongyang</namePart>
<namePart type="family">Shi</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>Existing neural-training-free AI-Generated Text (AIGT) detectors usually aggregate token-level probability signals with uniform weights. However, this ignores an important linguistic regularity: human-written and AI-generated texts exhibit different Part-Of-Speech (POS) n-gram patterns, making certain tokens more informative than others. To address the limitations, we propose SWLD-Joint (Syntax-pattern Weighted Log-likelihood Difference Joint Detection), a calibration-based neural-training-free detector without gradient-based optimization or neural classifier fine-tuning. SWLD-Joint first estimates POS n-gram template weights from labeled calibration data and then combines them with a POS-trajectory calibration signal to focus on syntactically informative positions. Experiments on DetectRL, RAID, and HC3_Ext show robust gains under domain shift, generator mismatch, and adversarial perturbations. Ablations, parameter analysis, case studies, score distributions, and ROC curves verify the effectiveness of syntax-pattern weighting. Code and data will be released upon acceptance.</abstract>
<identifier type="citekey">guo-etal-2026-tokens</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.1912</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1912/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>40743</start>
<end>40758</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Not All Tokens Are Equal: Syntax-Pattern Weighted Likelihood Difference Joint Detection for Neural-Training-Free AI-Generated Text Detection
%A Guo, Tianyu
%A Hao, Shufeng
%A Li, JiaQi
%A Shi, Chongyang
%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 guo-etal-2026-tokens
%X Existing neural-training-free AI-Generated Text (AIGT) detectors usually aggregate token-level probability signals with uniform weights. However, this ignores an important linguistic regularity: human-written and AI-generated texts exhibit different Part-Of-Speech (POS) n-gram patterns, making certain tokens more informative than others. To address the limitations, we propose SWLD-Joint (Syntax-pattern Weighted Log-likelihood Difference Joint Detection), a calibration-based neural-training-free detector without gradient-based optimization or neural classifier fine-tuning. SWLD-Joint first estimates POS n-gram template weights from labeled calibration data and then combines them with a POS-trajectory calibration signal to focus on syntactically informative positions. Experiments on DetectRL, RAID, and HC3_Ext show robust gains under domain shift, generator mismatch, and adversarial perturbations. Ablations, parameter analysis, case studies, score distributions, and ROC curves verify the effectiveness of syntax-pattern weighting. Code and data will be released upon acceptance.
%R 10.18653/2026.findings-emnlp.1912
%U https://aclanthology.org/2026.findings-emnlp.1912/
%U https://doi.org/10.18653/2026.findings-emnlp.1912
%P 40743-40758
Markdown (Informal)
[Not All Tokens Are Equal: Syntax-Pattern Weighted Likelihood Difference Joint Detection for Neural-Training-Free AI-Generated Text Detection](https://aclanthology.org/2026.findings-emnlp.1912/) (Guo et al., Findings 2026)
ACL