HCMUS_TheFangs at AbjadGenEval Shared Task: Weighted Layer Pooling with Attention Fusion for Arabic AI-Generated Text Detection

Duy Minh Dao Sy, Nguyen Chi Tran, Trung Kiet Huynh, Nguyen Lam Phu Quy, Pham Phu Hoa, Nguyen Dinh Ha Duong


Abstract
The rapid advancement of large language mod-els poses significant challenges for content au-thenticity, particularly in under-resourced lan-guages where detection tools remain scarce.We present our winning system for the Abjad-GenEval shared task on Arabic AI-generatedtext detection. Our key insight is that AI-generated text exhibits distinctive patternsacross multiple linguistic levels-from local syn-tax to global semantics-that can be captured bylearning to fuse representations from differenttransformer layers. We introduce aWeightedLayer Poolingmechanism that learns optimallayer combinations, combined withAttentionPoolingfor sequence-level context aggregation.Through systematic experimentation with 15+ approaches, we make a surprising discovery:model architecture selection dominates over so-phisticated training techniques, with DeBERTa-v3 providing +27% relative improvement overAraBERT regardless of training strategy. Oursystem achieves 0.93 F1-score, securing 1st placeamong all participants and outperform-ing the runner-up by 3 absolute points
Anthology ID:
2026.abjadnlp-1.51
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:
433–437
Language:
URL:
https://aclanthology.org/2026.abjadnlp-1.51/
DOI:
Bibkey:
Cite (ACL):
Duy Minh Dao Sy, Nguyen Chi Tran, Trung Kiet Huynh, Nguyen Lam Phu Quy, Pham Phu Hoa, and Nguyen Dinh Ha Duong. 2026. HCMUS_TheFangs at AbjadGenEval Shared Task: Weighted Layer Pooling with Attention Fusion for Arabic AI-Generated Text Detection. In Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script, pages 433–437, Rabat, Morocco. Association for Computational Linguistics.
Cite (Informal):
HCMUS_TheFangs at AbjadGenEval Shared Task: Weighted Layer Pooling with Attention Fusion for Arabic AI-Generated Text Detection (Dao Sy et al., AbjadNLP 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.abjadnlp-1.51.pdf