@inproceedings{orni-etal-2026-orni,
title = "Orni at {S}tance{E}val-2026: {A}rabic Stance Detection with Reasoning-Augmented {LLM} Prompting and Encoder Ensembles",
author = "Orni, Dipannita and
Ahmed, Kawsar and
Hoque, Mohammed Moshiul",
editor = "Abdul-Mageed, Muhammad and
Elsayed, Tamer and
Bouamor, Houda and
El-Beltagy, Samhaa and
Al-Khalifa, Hend and
Abdelali, Ahmed and
Elmadany, AbdelRahim and
El Mekki, Abdellah and
Darwish, Kareem and
Alkhereyf, Sakhar and
Luqman, Hamzah and
Khalifa, Salam and
Magdy, Samar and
Alyafeai, Zaid and
Hamed, Injy and
Zaghouani, Wajdi and
Zitouni, Imed",
booktitle = "Proceedings of The Fourth {A}rabic Natural Language Processing Conference: Shared Tasks",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-sharedtasks.81/",
pages = "642--650",
ISBN = "979-8-89176-497-2",
abstract = "Arabic stance detection is a task that identifies whether an Arabic text expresses Favor, Against, or None toward a given target. It is important for understanding public opinion and social media discourse, particularly in Arabic where dialectal variation, sarcasm, and informal expressions make stance interpretation difficult. To address this, we took part in StanceEval-2026 Track 1, where models are trained on provided targets and evaluated on a related target from the same thematic domain. We investigate two complementary approaches: fine-tuning-based systems using Arabic encoders and parameter-efficient LLM adaptation, and prompted GPT-4o without fine-tuning. Our experiments include encoder ensembles, multi-task and contrastive learning, attention aggregation, augmentation, calibration, QLoRA, and prompted LLMs with few-shot demonstrations, target-specific context, structured reasoning, and self-consistency voting. The best fine-tuning-based system achieves 0.701 Favg2, while GPT-4o v4 reaches 0.827 Favg2, 0.630 Favg3, and 0.784 accuracy, ranking 11th on the official leaderboard. The results show that prompted GPT-4o transfers more effectively to the related-target setting, while additional prompt complexity does not always lead to further improvement."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="orni-etal-2026-orni">
<titleInfo>
<title>Orni at StanceEval-2026: Arabic Stance Detection with Reasoning-Augmented LLM Prompting and Encoder Ensembles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dipannita</namePart>
<namePart type="family">Orni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kawsar</namePart>
<namePart type="family">Ahmed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Moshiul</namePart>
<namePart type="family">Hoque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamzah</namePart>
<namePart type="family">Luqman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-497-2</identifier>
</relatedItem>
<abstract>Arabic stance detection is a task that identifies whether an Arabic text expresses Favor, Against, or None toward a given target. It is important for understanding public opinion and social media discourse, particularly in Arabic where dialectal variation, sarcasm, and informal expressions make stance interpretation difficult. To address this, we took part in StanceEval-2026 Track 1, where models are trained on provided targets and evaluated on a related target from the same thematic domain. We investigate two complementary approaches: fine-tuning-based systems using Arabic encoders and parameter-efficient LLM adaptation, and prompted GPT-4o without fine-tuning. Our experiments include encoder ensembles, multi-task and contrastive learning, attention aggregation, augmentation, calibration, QLoRA, and prompted LLMs with few-shot demonstrations, target-specific context, structured reasoning, and self-consistency voting. The best fine-tuning-based system achieves 0.701 Favg2, while GPT-4o v4 reaches 0.827 Favg2, 0.630 Favg3, and 0.784 accuracy, ranking 11th on the official leaderboard. The results show that prompted GPT-4o transfers more effectively to the related-target setting, while additional prompt complexity does not always lead to further improvement.</abstract>
<identifier type="citekey">orni-etal-2026-orni</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.81/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>642</start>
<end>650</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Orni at StanceEval-2026: Arabic Stance Detection with Reasoning-Augmented LLM Prompting and Encoder Ensembles
%A Orni, Dipannita
%A Ahmed, Kawsar
%A Hoque, Mohammed Moshiul
%Y Abdul-Mageed, Muhammad
%Y Elsayed, Tamer
%Y Bouamor, Houda
%Y El-Beltagy, Samhaa
%Y Al-Khalifa, Hend
%Y Abdelali, Ahmed
%Y Elmadany, AbdelRahim
%Y El Mekki, Abdellah
%Y Darwish, Kareem
%Y Alkhereyf, Sakhar
%Y Luqman, Hamzah
%Y Khalifa, Salam
%Y Magdy, Samar
%Y Alyafeai, Zaid
%Y Hamed, Injy
%Y Zaghouani, Wajdi
%Y Zitouni, Imed
%S Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-497-2
%F orni-etal-2026-orni
%X Arabic stance detection is a task that identifies whether an Arabic text expresses Favor, Against, or None toward a given target. It is important for understanding public opinion and social media discourse, particularly in Arabic where dialectal variation, sarcasm, and informal expressions make stance interpretation difficult. To address this, we took part in StanceEval-2026 Track 1, where models are trained on provided targets and evaluated on a related target from the same thematic domain. We investigate two complementary approaches: fine-tuning-based systems using Arabic encoders and parameter-efficient LLM adaptation, and prompted GPT-4o without fine-tuning. Our experiments include encoder ensembles, multi-task and contrastive learning, attention aggregation, augmentation, calibration, QLoRA, and prompted LLMs with few-shot demonstrations, target-specific context, structured reasoning, and self-consistency voting. The best fine-tuning-based system achieves 0.701 Favg2, while GPT-4o v4 reaches 0.827 Favg2, 0.630 Favg3, and 0.784 accuracy, ranking 11th on the official leaderboard. The results show that prompted GPT-4o transfers more effectively to the related-target setting, while additional prompt complexity does not always lead to further improvement.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.81/
%P 642-650
Markdown (Informal)
[Orni at StanceEval-2026: Arabic Stance Detection with Reasoning-Augmented LLM Prompting and Encoder Ensembles](https://aclanthology.org/2026.arabicnlp-sharedtasks.81/) (Orni et al., ArabicNLP 2026)
ACL