@inproceedings{shen-2026-jlshen,
title = "{JLS}hen at {S}tance{E}val-2026: Cross-Lab {LLM} Ensembles and a Break-Even Rule for the Excluded Class",
author = "Shen, Junlong",
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.71/",
pages = "544--551",
ISBN = "979-8-89176-497-2",
abstract = "Our two systems for StanceEval-2026, Arabic stance detection on Mawqif-XT, placed 1st of 31 on Track 1 (Favg2 = 0.8994) and 2nd of 22 on Track 2 (0.9357). Track 1 averages six zero shot readings of each tweet by frontier models from two providers, and calls a fine-tuned Arabic pipeline only to break exact ties. Track 2 is one reader, given a short generated description of the target so it can score stance expressed through a related topic. The leaderboard publishes three aggregate scores over the same predictions, and reading them shows that about 60{\%} of our errors on both tracks are tweets annotated NONE that we placed in a stance class. Because the score ignores that class, the gain from moving such a row is fixed before the row is read. We derive the precision a repair must reach, and nine rankings plus an oracle from the corpus{'}s own annotation columns all fall short of it."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shen-2026-jlshen">
<titleInfo>
<title>JLShen at StanceEval-2026: Cross-Lab LLM Ensembles and a Break-Even Rule for the Excluded Class</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junlong</namePart>
<namePart type="family">Shen</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>Our two systems for StanceEval-2026, Arabic stance detection on Mawqif-XT, placed 1st of 31 on Track 1 (Favg2 = 0.8994) and 2nd of 22 on Track 2 (0.9357). Track 1 averages six zero shot readings of each tweet by frontier models from two providers, and calls a fine-tuned Arabic pipeline only to break exact ties. Track 2 is one reader, given a short generated description of the target so it can score stance expressed through a related topic. The leaderboard publishes three aggregate scores over the same predictions, and reading them shows that about 60% of our errors on both tracks are tweets annotated NONE that we placed in a stance class. Because the score ignores that class, the gain from moving such a row is fixed before the row is read. We derive the precision a repair must reach, and nine rankings plus an oracle from the corpus’s own annotation columns all fall short of it.</abstract>
<identifier type="citekey">shen-2026-jlshen</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.71/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>544</start>
<end>551</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JLShen at StanceEval-2026: Cross-Lab LLM Ensembles and a Break-Even Rule for the Excluded Class
%A Shen, Junlong
%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 shen-2026-jlshen
%X Our two systems for StanceEval-2026, Arabic stance detection on Mawqif-XT, placed 1st of 31 on Track 1 (Favg2 = 0.8994) and 2nd of 22 on Track 2 (0.9357). Track 1 averages six zero shot readings of each tweet by frontier models from two providers, and calls a fine-tuned Arabic pipeline only to break exact ties. Track 2 is one reader, given a short generated description of the target so it can score stance expressed through a related topic. The leaderboard publishes three aggregate scores over the same predictions, and reading them shows that about 60% of our errors on both tracks are tweets annotated NONE that we placed in a stance class. Because the score ignores that class, the gain from moving such a row is fixed before the row is read. We derive the precision a repair must reach, and nine rankings plus an oracle from the corpus’s own annotation columns all fall short of it.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.71/
%P 544-551
Markdown (Informal)
[JLShen at StanceEval-2026: Cross-Lab LLM Ensembles and a Break-Even Rule for the Excluded Class](https://aclanthology.org/2026.arabicnlp-sharedtasks.71/) (Shen, ArabicNLP 2026)
ACL