@inproceedings{alzahrany-etal-2026-makeen,
title = "Makeen at {AISA}-{A}rabic{FC}: Grounding {LLM} via Extracted Spans and Generalization Trade-off in {A}rabic Function Calling",
author = "Alzahrany, Nouf and
Korched, Abir and
Mattar, Bassam",
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.211/",
pages = "1635--1653",
ISBN = "979-8-89176-497-2",
abstract = "Reliable function calling is challenging for Arabic due to dialectal variation and limited task-specific resources. We present Makeen, a data-centric approach for the AISA-ArabicFC shared-task, and extend it with span extraction and confidence-gated routing. The best post-submission variant achieves 83.20{\%} argument exact match and 91.11{\%} Track B on development data under held-out (cross-validated) routing, while the submitted model achieves 82.65{\%} argument exact match and 91.06{\%} Track B on the blind test set, ranking 9th in Task B. We also release two Arabic tool-use datasets and show that external-tool augmentation improves unseen-tool argument exact match from 44.49{\%} to 66.53{\%}. These results highlight the importance of data quality, argument grounding, and tool-level generalization for Arabic function calling."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alzahrany-etal-2026-makeen">
<titleInfo>
<title>Makeen at AISA-ArabicFC: Grounding LLM via Extracted Spans and Generalization Trade-off in Arabic Function Calling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nouf</namePart>
<namePart type="family">Alzahrany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abir</namePart>
<namePart type="family">Korched</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bassam</namePart>
<namePart type="family">Mattar</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>Reliable function calling is challenging for Arabic due to dialectal variation and limited task-specific resources. We present Makeen, a data-centric approach for the AISA-ArabicFC shared-task, and extend it with span extraction and confidence-gated routing. The best post-submission variant achieves 83.20% argument exact match and 91.11% Track B on development data under held-out (cross-validated) routing, while the submitted model achieves 82.65% argument exact match and 91.06% Track B on the blind test set, ranking 9th in Task B. We also release two Arabic tool-use datasets and show that external-tool augmentation improves unseen-tool argument exact match from 44.49% to 66.53%. These results highlight the importance of data quality, argument grounding, and tool-level generalization for Arabic function calling.</abstract>
<identifier type="citekey">alzahrany-etal-2026-makeen</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.211/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1635</start>
<end>1653</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Makeen at AISA-ArabicFC: Grounding LLM via Extracted Spans and Generalization Trade-off in Arabic Function Calling
%A Alzahrany, Nouf
%A Korched, Abir
%A Mattar, Bassam
%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 alzahrany-etal-2026-makeen
%X Reliable function calling is challenging for Arabic due to dialectal variation and limited task-specific resources. We present Makeen, a data-centric approach for the AISA-ArabicFC shared-task, and extend it with span extraction and confidence-gated routing. The best post-submission variant achieves 83.20% argument exact match and 91.11% Track B on development data under held-out (cross-validated) routing, while the submitted model achieves 82.65% argument exact match and 91.06% Track B on the blind test set, ranking 9th in Task B. We also release two Arabic tool-use datasets and show that external-tool augmentation improves unseen-tool argument exact match from 44.49% to 66.53%. These results highlight the importance of data quality, argument grounding, and tool-level generalization for Arabic function calling.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.211/
%P 1635-1653
Markdown (Informal)
[Makeen at AISA-ArabicFC: Grounding LLM via Extracted Spans and Generalization Trade-off in Arabic Function Calling](https://aclanthology.org/2026.arabicnlp-sharedtasks.211/) (Alzahrany et al., ArabicNLP 2026)
ACL