@inproceedings{mohamed-etal-2026-nileun,
title = "{N}ile{U}n at {A}bjad{G}en{E}val Shared Task: Contrastive Learning with Stacking Ensemble for Efficient {A}rabic {AI}-Generated Text Detection",
author = "Mohamed, Mohamed Hussein and
Shalaby, Shrouk and
Mohamed, Nesreen",
booktitle = "Proceedings of the 2nd Workshop on {NLP} for Languages Using {A}rabic Script",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.abjadnlp-1.61/",
pages = "489--492",
abstract = "We present a computationally efficient ap- proach for detecting AI-generated Arabic text as part of the AbjadGenEval shared task. Our method combines Supervised Con- trastive Learning with a Stacking Ensemble of AraBERT and XLM-RoBERTa models. Our training pipeline progresses through three stages: (1) standard fine-tuning without con- trastive loss, (2) adding supervised contrastive loss for better embeddings, and (3) further fine-tuning on diverse generation styles. On our held-out test split, the stacking ensemble achieves F1=0.983 before fine-tuning. On the official workshop test data, our system achieved 4th place with F1=0.782, demonstrating strong generalization using only encoder-based trans- formers without requiring large language mod- els. Our implementation is publicly available"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohamed-etal-2026-nileun">
<titleInfo>
<title>NileUn at AbjadGenEval Shared Task: Contrastive Learning with Stacking Ensemble for Efficient Arabic AI-Generated Text Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="given">Hussein</namePart>
<namePart type="family">Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shrouk</namePart>
<namePart type="family">Shalaby</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nesreen</namePart>
<namePart type="family">Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a computationally efficient ap- proach for detecting AI-generated Arabic text as part of the AbjadGenEval shared task. Our method combines Supervised Con- trastive Learning with a Stacking Ensemble of AraBERT and XLM-RoBERTa models. Our training pipeline progresses through three stages: (1) standard fine-tuning without con- trastive loss, (2) adding supervised contrastive loss for better embeddings, and (3) further fine-tuning on diverse generation styles. On our held-out test split, the stacking ensemble achieves F1=0.983 before fine-tuning. On the official workshop test data, our system achieved 4th place with F1=0.782, demonstrating strong generalization using only encoder-based trans- formers without requiring large language mod- els. Our implementation is publicly available</abstract>
<identifier type="citekey">mohamed-etal-2026-nileun</identifier>
<location>
<url>https://aclanthology.org/2026.abjadnlp-1.61/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>489</start>
<end>492</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NileUn at AbjadGenEval Shared Task: Contrastive Learning with Stacking Ensemble for Efficient Arabic AI-Generated Text Detection
%A Mohamed, Mohamed Hussein
%A Shalaby, Shrouk
%A Mohamed, Nesreen
%S Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%F mohamed-etal-2026-nileun
%X We present a computationally efficient ap- proach for detecting AI-generated Arabic text as part of the AbjadGenEval shared task. Our method combines Supervised Con- trastive Learning with a Stacking Ensemble of AraBERT and XLM-RoBERTa models. Our training pipeline progresses through three stages: (1) standard fine-tuning without con- trastive loss, (2) adding supervised contrastive loss for better embeddings, and (3) further fine-tuning on diverse generation styles. On our held-out test split, the stacking ensemble achieves F1=0.983 before fine-tuning. On the official workshop test data, our system achieved 4th place with F1=0.782, demonstrating strong generalization using only encoder-based trans- formers without requiring large language mod- els. Our implementation is publicly available
%U https://aclanthology.org/2026.abjadnlp-1.61/
%P 489-492
Markdown (Informal)
[NileUn at AbjadGenEval Shared Task: Contrastive Learning with Stacking Ensemble for Efficient Arabic AI-Generated Text Detection](https://aclanthology.org/2026.abjadnlp-1.61/) (Mohamed et al., AbjadNLP 2026)
ACL