@inproceedings{alqaeri-etal-2026-thakaa-aisa,
title = "Thakaa at {AISA}-{A}rabic{FC}: Convention-Aligned Prompting and the Limits of Argument Exact Match in {A}rabic Function Calling",
author = "Alqaeri, Hassan and
Alamr, Meshal and
Aldahlawi, 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.210/",
pages = "1621--1634",
ISBN = "979-8-89176-497-2",
abstract = "Argument exact-match (ArgEM) dominates the AISA-ArabicFC score. Under one prompt, a base gemma-4-12B-it reaches 0.9853 FnAcc but only 0.6940 ArgEM on dev, suggesting that argument convention rather than tool selection is the binding constraint. Fine-tuning on the provided train split raises ArgEM to 0.8880 while FnAcc increases only from 0.9853 to 0.9945, yet the model still fails 8.4{\%} of the 10,500 positive training rows. Across rules, retrieval, prompting, selection, reranking, and fusion, dev-selected gains did not consistently transfer beyond development; smaller gains from other tested interventions remain unresolved. Explicit convention cards add 7.5 ArgEM points on a dev-selected 228-row subset for an unconfigured model, but give no measurable gain to the already configured pipeline. A scorer-equivalent gold answer occurs in a 20-sample pool for 34/56 (60.7{\%}) rows missed by the raw fine-tune, but our selectors cannot exploit it. Our official prompt-only gemma-4-31B-it submission placed 6th of 17 on Track A, 5th of 17 on Track B, and 4th of 21 on Track C. The 12B fine-tune used for analysis was developed first but inadvertently omitted from the blind-test submission, so it has no official test score."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alqaeri-etal-2026-thakaa-aisa">
<titleInfo>
<title>Thakaa at AISA-ArabicFC: Convention-Aligned Prompting and the Limits of Argument Exact Match in Arabic Function Calling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Alqaeri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meshal</namePart>
<namePart type="family">Alamr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="family">Aldahlawi</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>Argument exact-match (ArgEM) dominates the AISA-ArabicFC score. Under one prompt, a base gemma-4-12B-it reaches 0.9853 FnAcc but only 0.6940 ArgEM on dev, suggesting that argument convention rather than tool selection is the binding constraint. Fine-tuning on the provided train split raises ArgEM to 0.8880 while FnAcc increases only from 0.9853 to 0.9945, yet the model still fails 8.4% of the 10,500 positive training rows. Across rules, retrieval, prompting, selection, reranking, and fusion, dev-selected gains did not consistently transfer beyond development; smaller gains from other tested interventions remain unresolved. Explicit convention cards add 7.5 ArgEM points on a dev-selected 228-row subset for an unconfigured model, but give no measurable gain to the already configured pipeline. A scorer-equivalent gold answer occurs in a 20-sample pool for 34/56 (60.7%) rows missed by the raw fine-tune, but our selectors cannot exploit it. Our official prompt-only gemma-4-31B-it submission placed 6th of 17 on Track A, 5th of 17 on Track B, and 4th of 21 on Track C. The 12B fine-tune used for analysis was developed first but inadvertently omitted from the blind-test submission, so it has no official test score.</abstract>
<identifier type="citekey">alqaeri-etal-2026-thakaa-aisa</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.210/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1621</start>
<end>1634</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Thakaa at AISA-ArabicFC: Convention-Aligned Prompting and the Limits of Argument Exact Match in Arabic Function Calling
%A Alqaeri, Hassan
%A Alamr, Meshal
%A Aldahlawi, 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 alqaeri-etal-2026-thakaa-aisa
%X Argument exact-match (ArgEM) dominates the AISA-ArabicFC score. Under one prompt, a base gemma-4-12B-it reaches 0.9853 FnAcc but only 0.6940 ArgEM on dev, suggesting that argument convention rather than tool selection is the binding constraint. Fine-tuning on the provided train split raises ArgEM to 0.8880 while FnAcc increases only from 0.9853 to 0.9945, yet the model still fails 8.4% of the 10,500 positive training rows. Across rules, retrieval, prompting, selection, reranking, and fusion, dev-selected gains did not consistently transfer beyond development; smaller gains from other tested interventions remain unresolved. Explicit convention cards add 7.5 ArgEM points on a dev-selected 228-row subset for an unconfigured model, but give no measurable gain to the already configured pipeline. A scorer-equivalent gold answer occurs in a 20-sample pool for 34/56 (60.7%) rows missed by the raw fine-tune, but our selectors cannot exploit it. Our official prompt-only gemma-4-31B-it submission placed 6th of 17 on Track A, 5th of 17 on Track B, and 4th of 21 on Track C. The 12B fine-tune used for analysis was developed first but inadvertently omitted from the blind-test submission, so it has no official test score.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.210/
%P 1621-1634
Markdown (Informal)
[Thakaa at AISA-ArabicFC: Convention-Aligned Prompting and the Limits of Argument Exact Match in Arabic Function Calling](https://aclanthology.org/2026.arabicnlp-sharedtasks.210/) (Alqaeri et al., ArabicNLP 2026)
ACL