@inproceedings{alotaibi-2026-saliyah,
title = "saliyah at {S}tance{E}val-2026: Few-Shot {A}rabic {LLM}s and Complementary-Model Fusion for Stance Detection across Seen and Unseen Targets",
author = "Alotaibi, Saliyah",
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.80/",
pages = "636--641",
ISBN = "979-8-89176-497-2",
abstract = "We describe our entry to both tracks of StanceEval-2026, an Arabic stance-detection task built on the Mawqif-XT corpus. Track 1 (Seen Targets) is evaluated on Women Driving, while Track 2 (Unseen Targets) is evaluated on Electric Cars and the Trimester school calendar system. Rather than committing to a single approach, we compare two paradigms: fine-tuned Arabic encoders trained with multi-task learning using Mawqif-XT{'}s sentiment, sarcasm, and rationale annotations, and native Arabic LLMs used in a few-shot setting without any fine-tuning. For each track, we build the final system around the stronger approach. Across more than forty experimental configurations, few-shot LLMs consistently outperform fine-tuned encoders on both tracks. Our final systems achieve an Favg2 of 0.834 on Track 2 (ranked 9th) and 0.747 on Track 1 (ranked 13th), the latter through a complementary fusion of ALLaM-7B and Fanar-9B. We further observe that model performance may be related to how well pretraining coverage aligns with a target{'}s cultural and linguistic domain, that fusing two comparably strong models can outperform either model individually, and, perhaps most importantly, that more elaborate methods never surpass a strong LLM with a simple prompt. We release our code and prompts to support reproducibility."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alotaibi-2026-saliyah">
<titleInfo>
<title>saliyah at StanceEval-2026: Few-Shot Arabic LLMs and Complementary-Model Fusion for Stance Detection across Seen and Unseen Targets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saliyah</namePart>
<namePart type="family">Alotaibi</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 describe our entry to both tracks of StanceEval-2026, an Arabic stance-detection task built on the Mawqif-XT corpus. Track 1 (Seen Targets) is evaluated on Women Driving, while Track 2 (Unseen Targets) is evaluated on Electric Cars and the Trimester school calendar system. Rather than committing to a single approach, we compare two paradigms: fine-tuned Arabic encoders trained with multi-task learning using Mawqif-XT’s sentiment, sarcasm, and rationale annotations, and native Arabic LLMs used in a few-shot setting without any fine-tuning. For each track, we build the final system around the stronger approach. Across more than forty experimental configurations, few-shot LLMs consistently outperform fine-tuned encoders on both tracks. Our final systems achieve an Favg2 of 0.834 on Track 2 (ranked 9th) and 0.747 on Track 1 (ranked 13th), the latter through a complementary fusion of ALLaM-7B and Fanar-9B. We further observe that model performance may be related to how well pretraining coverage aligns with a target’s cultural and linguistic domain, that fusing two comparably strong models can outperform either model individually, and, perhaps most importantly, that more elaborate methods never surpass a strong LLM with a simple prompt. We release our code and prompts to support reproducibility.</abstract>
<identifier type="citekey">alotaibi-2026-saliyah</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.80/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>636</start>
<end>641</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T saliyah at StanceEval-2026: Few-Shot Arabic LLMs and Complementary-Model Fusion for Stance Detection across Seen and Unseen Targets
%A Alotaibi, Saliyah
%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 alotaibi-2026-saliyah
%X We describe our entry to both tracks of StanceEval-2026, an Arabic stance-detection task built on the Mawqif-XT corpus. Track 1 (Seen Targets) is evaluated on Women Driving, while Track 2 (Unseen Targets) is evaluated on Electric Cars and the Trimester school calendar system. Rather than committing to a single approach, we compare two paradigms: fine-tuned Arabic encoders trained with multi-task learning using Mawqif-XT’s sentiment, sarcasm, and rationale annotations, and native Arabic LLMs used in a few-shot setting without any fine-tuning. For each track, we build the final system around the stronger approach. Across more than forty experimental configurations, few-shot LLMs consistently outperform fine-tuned encoders on both tracks. Our final systems achieve an Favg2 of 0.834 on Track 2 (ranked 9th) and 0.747 on Track 1 (ranked 13th), the latter through a complementary fusion of ALLaM-7B and Fanar-9B. We further observe that model performance may be related to how well pretraining coverage aligns with a target’s cultural and linguistic domain, that fusing two comparably strong models can outperform either model individually, and, perhaps most importantly, that more elaborate methods never surpass a strong LLM with a simple prompt. We release our code and prompts to support reproducibility.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.80/
%P 636-641
Markdown (Informal)
[saliyah at StanceEval-2026: Few-Shot Arabic LLMs and Complementary-Model Fusion for Stance Detection across Seen and Unseen Targets](https://aclanthology.org/2026.arabicnlp-sharedtasks.80/) (Alotaibi, ArabicNLP 2026)
ACL