@inproceedings{almatrafi-2026-ahmednlp,
title = "{A}hmed{NLP} at {I}slamic{E}val 2026: Learning Answer Relevance from Within-Response Citation Preferences",
author = "Almatrafi, Ahmed",
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.128/",
pages = "1045--1049",
ISBN = "979-8-89176-497-2",
abstract = "IslamicEval 2026 Subtask 4 asks whether a Qur{'}anic or Hadith citation is useful for answering an Arabic question, rather than merely related to its topic. We treat this decision as ranking under shared response context. An Arabic instruction prompt is scored by the first answer-token logit difference between na{'}am ({''}yes'') and la ({''}no''). We adapt ALLaM 7B with LoRA and a response-balanced RankNet loss over 1,063 positive-negative pairs drawn from 348 mixed-label responses. At inference, the model uses deterministic logits and one calibrated threshold; it does not generate or sample an answer. On Development, the frozen checkpoint obtained 0.867761 Question Macro-F1 under question-grouped out-of-fold threshold calibration, compared with 0.777935 for zero-shot ALLaM. Our primary submission, AhmedNLP{\_}AllamR, scored 0.767880 on the official test and was the best of our three submitted runs. The largest Development-to-test drop occurred on all-negative questions. This result suggests retaining pairwise supervision while adding direct supervision for homogeneous negative groups."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="almatrafi-2026-ahmednlp">
<titleInfo>
<title>AhmedNLP at IslamicEval 2026: Learning Answer Relevance from Within-Response Citation Preferences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Almatrafi</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>IslamicEval 2026 Subtask 4 asks whether a Qur’anic or Hadith citation is useful for answering an Arabic question, rather than merely related to its topic. We treat this decision as ranking under shared response context. An Arabic instruction prompt is scored by the first answer-token logit difference between na’am (”yes”) and la (”no”). We adapt ALLaM 7B with LoRA and a response-balanced RankNet loss over 1,063 positive-negative pairs drawn from 348 mixed-label responses. At inference, the model uses deterministic logits and one calibrated threshold; it does not generate or sample an answer. On Development, the frozen checkpoint obtained 0.867761 Question Macro-F1 under question-grouped out-of-fold threshold calibration, compared with 0.777935 for zero-shot ALLaM. Our primary submission, AhmedNLP_AllamR, scored 0.767880 on the official test and was the best of our three submitted runs. The largest Development-to-test drop occurred on all-negative questions. This result suggests retaining pairwise supervision while adding direct supervision for homogeneous negative groups.</abstract>
<identifier type="citekey">almatrafi-2026-ahmednlp</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.128/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1045</start>
<end>1049</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings %T AhmedNLP at IslamicEval 2026: Learning Answer Relevance from Within-Response Citation Preferences %A Almatrafi, Ahmed %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 almatrafi-2026-ahmednlp %X IslamicEval 2026 Subtask 4 asks whether a Qur’anic or Hadith citation is useful for answering an Arabic question, rather than merely related to its topic. We treat this decision as ranking under shared response context. An Arabic instruction prompt is scored by the first answer-token logit difference between na’am (”yes”) and la (”no”). We adapt ALLaM 7B with LoRA and a response-balanced RankNet loss over 1,063 positive-negative pairs drawn from 348 mixed-label responses. At inference, the model uses deterministic logits and one calibrated threshold; it does not generate or sample an answer. On Development, the frozen checkpoint obtained 0.867761 Question Macro-F1 under question-grouped out-of-fold threshold calibration, compared with 0.777935 for zero-shot ALLaM. Our primary submission, AhmedNLP_AllamR, scored 0.767880 on the official test and was the best of our three submitted runs. The largest Development-to-test drop occurred on all-negative questions. This result suggests retaining pairwise supervision while adding direct supervision for homogeneous negative groups. %U https://aclanthology.org/2026.arabicnlp-sharedtasks.128/ %P 1045-1049
Markdown (Informal)
[AhmedNLP at IslamicEval 2026: Learning Answer Relevance from Within-Response Citation Preferences](https://aclanthology.org/2026.arabicnlp-sharedtasks.128/) (Almatrafi, ArabicNLP 2026)