@inproceedings{brandao-filho-etal-2026-akcit,
title = "{AKCIT} at {S}em{E}val-2026 Task 13: A Lightweight {L}ight{GBM} Baseline for Cross-Language Detection of {LLM}-Generated Code",
author = "Brandao Filho, Rone and
Rezende Rios, Walcy Santos and
Neves, Lucas and
Fleury Oliveira, Jose Ricardo and
Fernandes, Diogo and
Galv{\~a}o Filho, Arlindo",
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-1.417/",
pages = "3357--3362",
ISBN = "979-8-89176-414-9",
abstract = "The widespread use of LLMs in software development has made the detection of machine-generated code a pressing challenge, particularly when models must generalize across programming languages and domains. We present a lightweight, LLM-free pipeline that combines stylometric feature extraction with a LightGBM classifier and explicitly prioritizes structural generalization over deep semantic modeling. Despite its simplicity, the method achieves a Macro F1 of 0.70{--}0.72, more than doubling the CodeBERT baseline (0.30) in SemEval-2026 Task 13 Subtask A, while operating without GPUs or any fine-tuning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brandao-filho-etal-2026-akcit">
<titleInfo>
<title>AKCIT at SemEval-2026 Task 13: A Lightweight LightGBM Baseline for Cross-Language Detection of LLM-Generated Code</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rone</namePart>
<namePart type="family">Brandao Filho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walcy</namePart>
<namePart type="given">Santos</namePart>
<namePart type="family">Rezende Rios</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucas</namePart>
<namePart type="family">Neves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="given">Ricardo</namePart>
<namePart type="family">Fleury Oliveira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diogo</namePart>
<namePart type="family">Fernandes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arlindo</namePart>
<namePart type="family">Galvão Filho</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>The widespread use of LLMs in software development has made the detection of machine-generated code a pressing challenge, particularly when models must generalize across programming languages and domains. We present a lightweight, LLM-free pipeline that combines stylometric feature extraction with a LightGBM classifier and explicitly prioritizes structural generalization over deep semantic modeling. Despite its simplicity, the method achieves a Macro F1 of 0.70–0.72, more than doubling the CodeBERT baseline (0.30) in SemEval-2026 Task 13 Subtask A, while operating without GPUs or any fine-tuning.</abstract>
<identifier type="citekey">brandao-filho-etal-2026-akcit</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.417/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3357</start>
<end>3362</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AKCIT at SemEval-2026 Task 13: A Lightweight LightGBM Baseline for Cross-Language Detection of LLM-Generated Code
%A Brandao Filho, Rone
%A Rezende Rios, Walcy Santos
%A Neves, Lucas
%A Fleury Oliveira, Jose Ricardo
%A Fernandes, Diogo
%A Galvão Filho, Arlindo
%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 brandao-filho-etal-2026-akcit
%X The widespread use of LLMs in software development has made the detection of machine-generated code a pressing challenge, particularly when models must generalize across programming languages and domains. We present a lightweight, LLM-free pipeline that combines stylometric feature extraction with a LightGBM classifier and explicitly prioritizes structural generalization over deep semantic modeling. Despite its simplicity, the method achieves a Macro F1 of 0.70–0.72, more than doubling the CodeBERT baseline (0.30) in SemEval-2026 Task 13 Subtask A, while operating without GPUs or any fine-tuning.
%U https://aclanthology.org/2026.semeval-1.417/
%P 3357-3362
Markdown (Informal)
[AKCIT at SemEval-2026 Task 13: A Lightweight LightGBM Baseline for Cross-Language Detection of LLM-Generated Code](https://aclanthology.org/2026.semeval-1.417/) (Brandao Filho et al., SemEval 2026)
ACL