U4RASD at StanceNakba Shared Task: Data Augmentation and Auxiliary Objectives for Arabic Stance Detection

Nancy Hamdan, Aya Jouni, Aya Saïd, Fadi Zaraket


Abstract
This paper describes a submission to Track B of the StanceNakba Shared Task on Arabic cross-topic stance detection in the political domain. We investigate LLM-based data augmentation, auxiliary training objectives including contrastive and multi-task learning, zero-shot prompting, and a preliminary terminology-based clustering approach. Our final system, based on MARBERTv2 with dialect-aware LLM-based augmentation, achieved 86% macro-F1 on the blind test set and ranked 3rd out of 10 teams. Our results show that dialect-aware augmentation substantially improved performance in a low-resource Arabic stance detection setting, while not all auxiliary objectives or clustering-based strategies yielded consistent gains. We release our code at https://acr.ps/1L9B9Tw.
Anthology ID:
2026.nakbanlp-1.29
Volume:
Proceedings of the 2nd International Workshop on Nakba Narratives as Language Resources @ LREC 2026
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Mustafa Jarrar, Mo El-Haj, Amal Haddad, Serin Atiani, Shadi Abudalfa, Terry Regier, Paul Rayson, Khalil Sima’an, Camille Mansour
Venues:
NakbaNLP | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
206–211
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-nakbanlp-29
DOI:
10.63317/2dsxtdvvu8vu
Bibkey:
Cite (ACL):
Nancy Hamdan, Aya Jouni, Aya Saïd, and Fadi Zaraket. 2026. U4RASD at StanceNakba Shared Task: Data Augmentation and Auxiliary Objectives for Arabic Stance Detection. In Proceedings of the 2nd International Workshop on Nakba Narratives as Language Resources @ LREC 2026, pages 206–211, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
U4RASD at StanceNakba Shared Task: Data Augmentation and Auxiliary Objectives for Arabic Stance Detection (Hamdan et al., NakbaNLP 2026)
Copy Citation: