@inproceedings{alamr-etal-2026-thakaa,
title = "Thakaa at {S}tance{E}val-2026: Inference-Time Target Grounding for {A}rabic Stance Detection",
author = "Alamr, Meshal and
Alqaeri, Hassan and
Aldahlawi, Abdullah",
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.82/",
pages = "651--655",
ISBN = "979-8-89176-497-2",
abstract = "StanceEval-2026 tests Arabic stance classification under target shift, with evaluation targets absent from the labelled task data. We test two ways to supply target information at inference time. For Track 1, we retrieve eight labelled Women Driving demonstrations from the external ArabicStanceX corpus and score the three label tokens with Gemma-4-31B-IT. For the unseen-target track, we prepend cached target context prompted to be factual and non-evaluative, then fuse label predictions and label-token scores from multiple LLMs, with final assignments constrained by published class totals. The systems obtain 85.22 and 91.78 $F_{\mathrm{avg2}}$ on Tracks 1 and 2, ranking sixth and fourth in the final standings. On held-out ArabicStanceX tweets, direct prompting scores 79.45 $F_{\mathrm{avg2}}$; eight random Women Driving demonstrations raise it to 84.78, and similarity retrieval reaches 89.04. Across three target-held-out Mawqif evaluations, a fixed target card raises Gemma-4-31B-IT from 86.54 to 86.93, whereas QLoRA lowers Gemma-4-12B-IT from 84.43 to 83.77. In these separate public evaluations, same-target demonstrations and retrieval improve performance, factual target context provides small, target-dependent gains, and the tested source-only adapter does not improve."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alamr-etal-2026-thakaa">
<titleInfo>
<title>Thakaa at StanceEval-2026: Inference-Time Target Grounding for Arabic Stance Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Meshal</namePart>
<namePart type="family">Alamr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Alqaeri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="family">Aldahlawi</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>StanceEval-2026 tests Arabic stance classification under target shift, with evaluation targets absent from the labelled task data. We test two ways to supply target information at inference time. For Track 1, we retrieve eight labelled Women Driving demonstrations from the external ArabicStanceX corpus and score the three label tokens with Gemma-4-31B-IT. For the unseen-target track, we prepend cached target context prompted to be factual and non-evaluative, then fuse label predictions and label-token scores from multiple LLMs, with final assignments constrained by published class totals. The systems obtain 85.22 and 91.78 F_avg2 on Tracks 1 and 2, ranking sixth and fourth in the final standings. On held-out ArabicStanceX tweets, direct prompting scores 79.45 F_avg2; eight random Women Driving demonstrations raise it to 84.78, and similarity retrieval reaches 89.04. Across three target-held-out Mawqif evaluations, a fixed target card raises Gemma-4-31B-IT from 86.54 to 86.93, whereas QLoRA lowers Gemma-4-12B-IT from 84.43 to 83.77. In these separate public evaluations, same-target demonstrations and retrieval improve performance, factual target context provides small, target-dependent gains, and the tested source-only adapter does not improve.</abstract>
<identifier type="citekey">alamr-etal-2026-thakaa</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.82/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>651</start>
<end>655</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Thakaa at StanceEval-2026: Inference-Time Target Grounding for Arabic Stance Detection
%A Alamr, Meshal
%A Alqaeri, Hassan
%A Aldahlawi, Abdullah
%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 alamr-etal-2026-thakaa
%X StanceEval-2026 tests Arabic stance classification under target shift, with evaluation targets absent from the labelled task data. We test two ways to supply target information at inference time. For Track 1, we retrieve eight labelled Women Driving demonstrations from the external ArabicStanceX corpus and score the three label tokens with Gemma-4-31B-IT. For the unseen-target track, we prepend cached target context prompted to be factual and non-evaluative, then fuse label predictions and label-token scores from multiple LLMs, with final assignments constrained by published class totals. The systems obtain 85.22 and 91.78 F_avg2 on Tracks 1 and 2, ranking sixth and fourth in the final standings. On held-out ArabicStanceX tweets, direct prompting scores 79.45 F_avg2; eight random Women Driving demonstrations raise it to 84.78, and similarity retrieval reaches 89.04. Across three target-held-out Mawqif evaluations, a fixed target card raises Gemma-4-31B-IT from 86.54 to 86.93, whereas QLoRA lowers Gemma-4-12B-IT from 84.43 to 83.77. In these separate public evaluations, same-target demonstrations and retrieval improve performance, factual target context provides small, target-dependent gains, and the tested source-only adapter does not improve.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.82/
%P 651-655
Markdown (Informal)
[Thakaa at StanceEval-2026: Inference-Time Target Grounding for Arabic Stance Detection](https://aclanthology.org/2026.arabicnlp-sharedtasks.82/) (Alamr et al., ArabicNLP 2026)
ACL