@inproceedings{ehsan-qamar-2026-hardstance,
title = "{H}ard{S}tance at {S}tance{E}val-2026: Error-Driven Prompt Calibration for {A}rabic Stance Detection",
author = "Ehsan, Abdullah and
Qamar, Faiza",
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.76/",
pages = "602--612",
ISBN = "979-8-89176-497-2",
abstract = "We present our system for StanceEval-2026 Track 1, which focuses on Arabic stance detection toward \textit{Women Driving} using the Mawqif-v2 dataset with three labels: Favor, Against, and None. We compare fine-tuned AraBERT models with zero-shot Gemma-4-31B. We refine the Gemma prompt using recurring development-set errors, focusing on dialect and indirect meaning, target identification, sentiment versus stance, hashtags, sarcasm, and the distinction between reporting and endorsement. We also compare the calibrated system with several alternative inference strategies, including self-consistency, model debate, and dialect-interpreter pipelines. The final Gemma-4-31B system achieves 86.61{\%} Favg2, 67.46{\%} Favg3, and 82.67{\%} accuracy on the official blind test, ranking 5th. Our results show that target-specific context and clear decision rules can be more effective than adding additional inference stages or model interactions. The main remaining challenge is distinguishing \textit{Against} from \textit{None}, particularly when stance is indirect, ambiguous, or expressed through humor."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ehsan-qamar-2026-hardstance">
<titleInfo>
<title>HardStance at StanceEval-2026: Error-Driven Prompt Calibration for Arabic Stance Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="family">Ehsan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Faiza</namePart>
<namePart type="family">Qamar</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>We present our system for StanceEval-2026 Track 1, which focuses on Arabic stance detection toward Women Driving using the Mawqif-v2 dataset with three labels: Favor, Against, and None. We compare fine-tuned AraBERT models with zero-shot Gemma-4-31B. We refine the Gemma prompt using recurring development-set errors, focusing on dialect and indirect meaning, target identification, sentiment versus stance, hashtags, sarcasm, and the distinction between reporting and endorsement. We also compare the calibrated system with several alternative inference strategies, including self-consistency, model debate, and dialect-interpreter pipelines. The final Gemma-4-31B system achieves 86.61% Favg2, 67.46% Favg3, and 82.67% accuracy on the official blind test, ranking 5th. Our results show that target-specific context and clear decision rules can be more effective than adding additional inference stages or model interactions. The main remaining challenge is distinguishing Against from None, particularly when stance is indirect, ambiguous, or expressed through humor.</abstract>
<identifier type="citekey">ehsan-qamar-2026-hardstance</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.76/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>602</start>
<end>612</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HardStance at StanceEval-2026: Error-Driven Prompt Calibration for Arabic Stance Detection
%A Ehsan, Abdullah
%A Qamar, Faiza
%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 ehsan-qamar-2026-hardstance
%X We present our system for StanceEval-2026 Track 1, which focuses on Arabic stance detection toward Women Driving using the Mawqif-v2 dataset with three labels: Favor, Against, and None. We compare fine-tuned AraBERT models with zero-shot Gemma-4-31B. We refine the Gemma prompt using recurring development-set errors, focusing on dialect and indirect meaning, target identification, sentiment versus stance, hashtags, sarcasm, and the distinction between reporting and endorsement. We also compare the calibrated system with several alternative inference strategies, including self-consistency, model debate, and dialect-interpreter pipelines. The final Gemma-4-31B system achieves 86.61% Favg2, 67.46% Favg3, and 82.67% accuracy on the official blind test, ranking 5th. Our results show that target-specific context and clear decision rules can be more effective than adding additional inference stages or model interactions. The main remaining challenge is distinguishing Against from None, particularly when stance is indirect, ambiguous, or expressed through humor.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.76/
%P 602-612
Markdown (Informal)
[HardStance at StanceEval-2026: Error-Driven Prompt Calibration for Arabic Stance Detection](https://aclanthology.org/2026.arabicnlp-sharedtasks.76/) (Ehsan & Qamar, ArabicNLP 2026)
ACL