NileUn at AbjadGenEval Shared Task: Contrastive Learning with Stacking Ensemble for Efficient Arabic AI-Generated Text Detection

Mohamed Hussein Mohamed, Shrouk Shalaby, Nesreen Mohamed


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
Anthology ID:
2026.abjadnlp-1.61
Volume:
Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script
Month:
March
Year:
2026
Address:
Rabat, Morocco
Venues:
AbjadNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
489–492
Language:
URL:
https://aclanthology.org/2026.abjadnlp-1.61/
DOI:
Bibkey:
Cite (ACL):
Mohamed Hussein Mohamed, Shrouk Shalaby, and Nesreen Mohamed. 2026. NileUn at AbjadGenEval Shared Task: Contrastive Learning with Stacking Ensemble for Efficient Arabic AI-Generated Text Detection. In Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script, pages 489–492, Rabat, Morocco. Association for Computational Linguistics.
Cite (Informal):
NileUn at AbjadGenEval Shared Task: Contrastive Learning with Stacking Ensemble for Efficient Arabic AI-Generated Text Detection (Mohamed et al., AbjadNLP 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.abjadnlp-1.61.pdf