@inproceedings{alowaidi-2026-hade,
title = "{H}a{D}e at {I}slamic{E}val 2026: Evaluating Prompted Judgment and Fine-Tuned Encoders for Islamic Citation Relevance",
author = "Alowaidi, Sanaa",
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.130/",
pages = "1055--1066",
ISBN = "979-8-89176-497-2",
abstract = "This paper presents our participation in IslamicEval 2026 Subtask 4, citation relevance classification for Qur{'}an and Hadith spans. We propose two independent systems for this task. The first is a generative large language model prompted to produce a structured, step by step relevance judgment. The second is a domain pretrained sentence encoder fine tuned with triplet loss on citation relevance data. Our evaluation compares two generative backends and three encoders pretrained on different Arabic varieties, using macro averaged F1 as the metric. Results show on development set that chain of thought judgment with ALLaM-7B consistently outperforms our embedding similarity ensemble, reaching 0.774 macro F1 against 0.357 for the ensemble, and outperforms an equivalent Fanar-S-1-7B system on seven of eight prompting strategies. Additionally, AraBERT-v02, pretrained on Modern Standard Arabic, is the consistently strongest encoder, outperforming Classical Arabic pretrained encoders in this citation relevance task. Our best submitted system, ALLaM with few shot prompting without chain of thought, scores 0.748 macro F1 on the blind test set, narrowly ahead of the same backend with chain of thought added, at 0.744."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alowaidi-2026-hade">
<titleInfo>
<title>HaDe at IslamicEval 2026: Evaluating Prompted Judgment and Fine-Tuned Encoders for Islamic Citation Relevance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanaa</namePart>
<namePart type="family">Alowaidi</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>This paper presents our participation in IslamicEval 2026 Subtask 4, citation relevance classification for Qur’an and Hadith spans. We propose two independent systems for this task. The first is a generative large language model prompted to produce a structured, step by step relevance judgment. The second is a domain pretrained sentence encoder fine tuned with triplet loss on citation relevance data. Our evaluation compares two generative backends and three encoders pretrained on different Arabic varieties, using macro averaged F1 as the metric. Results show on development set that chain of thought judgment with ALLaM-7B consistently outperforms our embedding similarity ensemble, reaching 0.774 macro F1 against 0.357 for the ensemble, and outperforms an equivalent Fanar-S-1-7B system on seven of eight prompting strategies. Additionally, AraBERT-v02, pretrained on Modern Standard Arabic, is the consistently strongest encoder, outperforming Classical Arabic pretrained encoders in this citation relevance task. Our best submitted system, ALLaM with few shot prompting without chain of thought, scores 0.748 macro F1 on the blind test set, narrowly ahead of the same backend with chain of thought added, at 0.744.</abstract>
<identifier type="citekey">alowaidi-2026-hade</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.130/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1055</start>
<end>1066</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HaDe at IslamicEval 2026: Evaluating Prompted Judgment and Fine-Tuned Encoders for Islamic Citation Relevance
%A Alowaidi, Sanaa
%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 alowaidi-2026-hade
%X This paper presents our participation in IslamicEval 2026 Subtask 4, citation relevance classification for Qur’an and Hadith spans. We propose two independent systems for this task. The first is a generative large language model prompted to produce a structured, step by step relevance judgment. The second is a domain pretrained sentence encoder fine tuned with triplet loss on citation relevance data. Our evaluation compares two generative backends and three encoders pretrained on different Arabic varieties, using macro averaged F1 as the metric. Results show on development set that chain of thought judgment with ALLaM-7B consistently outperforms our embedding similarity ensemble, reaching 0.774 macro F1 against 0.357 for the ensemble, and outperforms an equivalent Fanar-S-1-7B system on seven of eight prompting strategies. Additionally, AraBERT-v02, pretrained on Modern Standard Arabic, is the consistently strongest encoder, outperforming Classical Arabic pretrained encoders in this citation relevance task. Our best submitted system, ALLaM with few shot prompting without chain of thought, scores 0.748 macro F1 on the blind test set, narrowly ahead of the same backend with chain of thought added, at 0.744.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.130/
%P 1055-1066
Markdown (Informal)
[HaDe at IslamicEval 2026: Evaluating Prompted Judgment and Fine-Tuned Encoders for Islamic Citation Relevance](https://aclanthology.org/2026.arabicnlp-sharedtasks.130/) (Alowaidi, ArabicNLP 2026)
ACL