@inproceedings{pham-etal-2026-uit,
title = "{UIT}-{AMMC} at {S}em{E}val-2026 Task 13: Exploiting Structural Formatting Signatures for Robust {AI}-Generated Code Detection",
author = "Pham, Cuong and
Nguyen, Minh and
Le, Minh and
Nguyen, An and
Nguyen, Chinh",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.60/",
pages = "418--425",
ISBN = "979-8-89176-414-9",
abstract = "We participated in Subtask A with our Structure-Aware Contrastive Cascade, a multi-stage architecture designed to distinguish between human-authored and machine-generated code by integrating generative reasoning with explicit structural linguistic features. Our system focuses on exploiting structural formatting signatures that frequently emerge in AI-generated code as a byproduct of post-training alignment and readability optimization. The pipeline utilizes a Qwen-2.5-Coder 14B model fine-tuned via QLoRA, incorporating stochastic data augmentation techniques to ensure robustness across unseen programming languages. Final classification is achieved through a late-fusion mechanism that combines contrastive probability scores with statistical metrics of code presentation density. For samples exhibiting high epistemic uncertainty, we implement a multi-agent adversarial debate step to refine the final verdict. This approach enabled our system to achieve a Macro F1 score of 0.802, ranking 3rd on the official leaderboard."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pham-etal-2026-uit">
<titleInfo>
<title>UIT-AMMC at SemEval-2026 Task 13: Exploiting Structural Formatting Signatures for Robust AI-Generated Code Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cuong</namePart>
<namePart type="family">Pham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minh</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minh</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">An</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chinh</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>We participated in Subtask A with our Structure-Aware Contrastive Cascade, a multi-stage architecture designed to distinguish between human-authored and machine-generated code by integrating generative reasoning with explicit structural linguistic features. Our system focuses on exploiting structural formatting signatures that frequently emerge in AI-generated code as a byproduct of post-training alignment and readability optimization. The pipeline utilizes a Qwen-2.5-Coder 14B model fine-tuned via QLoRA, incorporating stochastic data augmentation techniques to ensure robustness across unseen programming languages. Final classification is achieved through a late-fusion mechanism that combines contrastive probability scores with statistical metrics of code presentation density. For samples exhibiting high epistemic uncertainty, we implement a multi-agent adversarial debate step to refine the final verdict. This approach enabled our system to achieve a Macro F1 score of 0.802, ranking 3rd on the official leaderboard.</abstract>
<identifier type="citekey">pham-etal-2026-uit</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.60/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>418</start>
<end>425</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UIT-AMMC at SemEval-2026 Task 13: Exploiting Structural Formatting Signatures for Robust AI-Generated Code Detection
%A Pham, Cuong
%A Nguyen, Minh
%A Le, Minh
%A Nguyen, An
%A Nguyen, Chinh
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F pham-etal-2026-uit
%X We participated in Subtask A with our Structure-Aware Contrastive Cascade, a multi-stage architecture designed to distinguish between human-authored and machine-generated code by integrating generative reasoning with explicit structural linguistic features. Our system focuses on exploiting structural formatting signatures that frequently emerge in AI-generated code as a byproduct of post-training alignment and readability optimization. The pipeline utilizes a Qwen-2.5-Coder 14B model fine-tuned via QLoRA, incorporating stochastic data augmentation techniques to ensure robustness across unseen programming languages. Final classification is achieved through a late-fusion mechanism that combines contrastive probability scores with statistical metrics of code presentation density. For samples exhibiting high epistemic uncertainty, we implement a multi-agent adversarial debate step to refine the final verdict. This approach enabled our system to achieve a Macro F1 score of 0.802, ranking 3rd on the official leaderboard.
%U https://aclanthology.org/2026.semeval-1.60/
%P 418-425
Markdown (Informal)
[UIT-AMMC at SemEval-2026 Task 13: Exploiting Structural Formatting Signatures for Robust AI-Generated Code Detection](https://aclanthology.org/2026.semeval-1.60/) (Pham et al., SemEval 2026)
ACL