@inproceedings{alanazi-alshammari-2026-siraj,
title = "Siraj at {AISA}-{A}rabic{FC}: Selective Argument Repair and the Limits of Post-Editing in {A}rabic Function Calling",
author = "Alanazi, Abdullah G. and
Alshammari, Reem K.",
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.205/",
pages = "1592--1596",
ISBN = "979-8-89176-497-2",
abstract = "We describe Siraj{'}s Track B submission to AISA-ArabicFC. A QLoRA-tuned ALLaM-7B is followed by a separately trained argument repairer whose edits pass a type-restricted acceptance filter, then by one deterministic year rule. On the blind test set (1,125 rows) it scores 0.8245 ArgEM and 0.9101 Track B, 10th of 17 systems; the post-editing stage is worth about one example on test against four on development. Every rule that error inspection suggested was adjudicated on out-of-fold training predictions, scored with the task{'}s own published matcher, before it could touch development predictions; all five were rejected, one of them breaking 168 more rows than it fixed. Two development-time conclusions did not survive: the top three systems finished 5.5 to 5.7 ArgEM points ahead, so our error rate was not a task-level ceiling, and a later dataset revision lowers our development ArgEM from 0.850 to 0.8080 and neutralises our strongest rule. Post-editing rules fitted to gold conventions can inherit changes in those conventions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alanazi-alshammari-2026-siraj">
<titleInfo>
<title>Siraj at AISA-ArabicFC: Selective Argument Repair and the Limits of Post-Editing in Arabic Function Calling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="given">G</namePart>
<namePart type="family">Alanazi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reem</namePart>
<namePart type="given">K</namePart>
<namePart type="family">Alshammari</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 Siraj’s Track B submission to AISA-ArabicFC. A QLoRA-tuned ALLaM-7B is followed by a separately trained argument repairer whose edits pass a type-restricted acceptance filter, then by one deterministic year rule. On the blind test set (1,125 rows) it scores 0.8245 ArgEM and 0.9101 Track B, 10th of 17 systems; the post-editing stage is worth about one example on test against four on development. Every rule that error inspection suggested was adjudicated on out-of-fold training predictions, scored with the task’s own published matcher, before it could touch development predictions; all five were rejected, one of them breaking 168 more rows than it fixed. Two development-time conclusions did not survive: the top three systems finished 5.5 to 5.7 ArgEM points ahead, so our error rate was not a task-level ceiling, and a later dataset revision lowers our development ArgEM from 0.850 to 0.8080 and neutralises our strongest rule. Post-editing rules fitted to gold conventions can inherit changes in those conventions.</abstract>
<identifier type="citekey">alanazi-alshammari-2026-siraj</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.205/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1592</start>
<end>1596</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Siraj at AISA-ArabicFC: Selective Argument Repair and the Limits of Post-Editing in Arabic Function Calling
%A Alanazi, Abdullah G.
%A Alshammari, Reem K.
%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 alanazi-alshammari-2026-siraj
%X We describe Siraj’s Track B submission to AISA-ArabicFC. A QLoRA-tuned ALLaM-7B is followed by a separately trained argument repairer whose edits pass a type-restricted acceptance filter, then by one deterministic year rule. On the blind test set (1,125 rows) it scores 0.8245 ArgEM and 0.9101 Track B, 10th of 17 systems; the post-editing stage is worth about one example on test against four on development. Every rule that error inspection suggested was adjudicated on out-of-fold training predictions, scored with the task’s own published matcher, before it could touch development predictions; all five were rejected, one of them breaking 168 more rows than it fixed. Two development-time conclusions did not survive: the top three systems finished 5.5 to 5.7 ArgEM points ahead, so our error rate was not a task-level ceiling, and a later dataset revision lowers our development ArgEM from 0.850 to 0.8080 and neutralises our strongest rule. Post-editing rules fitted to gold conventions can inherit changes in those conventions.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.205/
%P 1592-1596
Markdown (Informal)
[Siraj at AISA-ArabicFC: Selective Argument Repair and the Limits of Post-Editing in Arabic Function Calling](https://aclanthology.org/2026.arabicnlp-sharedtasks.205/) (Alanazi & Alshammari, ArabicNLP 2026)
ACL