@inproceedings{almohammedi-2026-saudi,
title = "Saudi Legal {FC} at {AISA}-{A}rabic{FC}: Disciplined Fine-Tuning and Gold-Free Post-Processing for {A}rabic Function Calling",
author = "Almohammedi, 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.199/",
pages = "1547--1551",
ISBN = "979-8-89176-497-2",
abstract = "We describe the Saudi Legal FC submission to the AISA-ArabicFC shared task on Arabic function calling. Our system is a parameter-efficient fine-tune of Qwen2.5-7B-Instruct with LoRA, trained with completion-only loss masking. Beyond the model, our central contribution is methodological: we use written, falsifiable score predictions and a validated local scorer to gate submissions, with a post-processing safety net that uses no gold at inference. On the public development set our best configuration reaches Argument Exact-Match (ArgEM) 0.828 and function-name accuracy 1.0 (Overall-B 0.914) under the official v1.3 evaluator. Its weights were then lost; the blind submission comes from a reconstruction selected against that model{'}s frozen predictions, and ranks 12th on Track B with Overall-B 0.8946. We also report two negative findings{---}one retraining run, one rejected hypothesis{---}and an artifact-identity failure our behavioral checks caught before submission."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="almohammedi-2026-saudi">
<titleInfo>
<title>Saudi Legal FC at AISA-ArabicFC: Disciplined Fine-Tuning and Gold-Free Post-Processing for Arabic Function Calling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="family">Almohammedi</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 the Saudi Legal FC submission to the AISA-ArabicFC shared task on Arabic function calling. Our system is a parameter-efficient fine-tune of Qwen2.5-7B-Instruct with LoRA, trained with completion-only loss masking. Beyond the model, our central contribution is methodological: we use written, falsifiable score predictions and a validated local scorer to gate submissions, with a post-processing safety net that uses no gold at inference. On the public development set our best configuration reaches Argument Exact-Match (ArgEM) 0.828 and function-name accuracy 1.0 (Overall-B 0.914) under the official v1.3 evaluator. Its weights were then lost; the blind submission comes from a reconstruction selected against that model’s frozen predictions, and ranks 12th on Track B with Overall-B 0.8946. We also report two negative findings—one retraining run, one rejected hypothesis—and an artifact-identity failure our behavioral checks caught before submission.</abstract>
<identifier type="citekey">almohammedi-2026-saudi</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.199/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1547</start>
<end>1551</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Saudi Legal FC at AISA-ArabicFC: Disciplined Fine-Tuning and Gold-Free Post-Processing for Arabic Function Calling
%A Almohammedi, 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 almohammedi-2026-saudi
%X We describe the Saudi Legal FC submission to the AISA-ArabicFC shared task on Arabic function calling. Our system is a parameter-efficient fine-tune of Qwen2.5-7B-Instruct with LoRA, trained with completion-only loss masking. Beyond the model, our central contribution is methodological: we use written, falsifiable score predictions and a validated local scorer to gate submissions, with a post-processing safety net that uses no gold at inference. On the public development set our best configuration reaches Argument Exact-Match (ArgEM) 0.828 and function-name accuracy 1.0 (Overall-B 0.914) under the official v1.3 evaluator. Its weights were then lost; the blind submission comes from a reconstruction selected against that model’s frozen predictions, and ranks 12th on Track B with Overall-B 0.8946. We also report two negative findings—one retraining run, one rejected hypothesis—and an artifact-identity failure our behavioral checks caught before submission.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.199/
%P 1547-1551
Markdown (Informal)
[Saudi Legal FC at AISA-ArabicFC: Disciplined Fine-Tuning and Gold-Free Post-Processing for Arabic Function Calling](https://aclanthology.org/2026.arabicnlp-sharedtasks.199/) (Almohammedi, ArabicNLP 2026)
ACL