@inproceedings{lakab-etal-2026-abjad,
title = "Abjad at {AISA}-{A}rabic{FC}: Error Analysis and Prompt Engineering for {A}rabic Function Calling",
author = "Lakab, Randa and
Alsultan, Shahad Abdulaziz Abdullah and
Almutiri, Abrar",
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.204/",
pages = "1585--1591",
ISBN = "979-8-89176-497-2",
abstract = "We describe Abjad{'}s submission to the AISA-ArabicFC shared task (Track B), which targets Arabic function calling with explicit natural-language reasoning prior to the structured call. Rather than fine-tuning, our system builds a robust inference and evaluation pipeline around the organizers' baseline model, AISA-AR-FunctionCall-Think, diagnosing and fixing two pipeline-level bugs that were silently depressing scores. On the 545-example development set, our system reaches a function-name accuracy of 96.15{\%} but an argument exact-match of only 40.6{\%}, yielding an official Track B score (overall{\_}b) of 0.6665, below the organizer-reported baseline of 0.739. We present a fine-grained error analysis showing that failures concentrate almost entirely in argument value formatting, including currency codes, ISO language codes, and transliteration, rather than in tool selection or task comprehension. These findings suggest that targeted fine-tuning or post-processing for structured-value normalization is a promising direction for improving Arabic function-calling performance. abjad aisa arabicfc.pdf"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lakab-etal-2026-abjad">
<titleInfo>
<title>Abjad at AISA-ArabicFC: Error Analysis and Prompt Engineering for Arabic Function Calling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Randa</namePart>
<namePart type="family">Lakab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahad</namePart>
<namePart type="given">Abdulaziz</namePart>
<namePart type="given">Abdullah</namePart>
<namePart type="family">Alsultan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abrar</namePart>
<namePart type="family">Almutiri</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 Abjad’s submission to the AISA-ArabicFC shared task (Track B), which targets Arabic function calling with explicit natural-language reasoning prior to the structured call. Rather than fine-tuning, our system builds a robust inference and evaluation pipeline around the organizers’ baseline model, AISA-AR-FunctionCall-Think, diagnosing and fixing two pipeline-level bugs that were silently depressing scores. On the 545-example development set, our system reaches a function-name accuracy of 96.15% but an argument exact-match of only 40.6%, yielding an official Track B score (overall_b) of 0.6665, below the organizer-reported baseline of 0.739. We present a fine-grained error analysis showing that failures concentrate almost entirely in argument value formatting, including currency codes, ISO language codes, and transliteration, rather than in tool selection or task comprehension. These findings suggest that targeted fine-tuning or post-processing for structured-value normalization is a promising direction for improving Arabic function-calling performance. abjad aisa arabicfc.pdf</abstract>
<identifier type="citekey">lakab-etal-2026-abjad</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.204/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1585</start>
<end>1591</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings %T Abjad at AISA-ArabicFC: Error Analysis and Prompt Engineering for Arabic Function Calling %A Lakab, Randa %A Alsultan, Shahad Abdulaziz Abdullah %A Almutiri, Abrar %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 lakab-etal-2026-abjad %X We describe Abjad’s submission to the AISA-ArabicFC shared task (Track B), which targets Arabic function calling with explicit natural-language reasoning prior to the structured call. Rather than fine-tuning, our system builds a robust inference and evaluation pipeline around the organizers’ baseline model, AISA-AR-FunctionCall-Think, diagnosing and fixing two pipeline-level bugs that were silently depressing scores. On the 545-example development set, our system reaches a function-name accuracy of 96.15% but an argument exact-match of only 40.6%, yielding an official Track B score (overall_b) of 0.6665, below the organizer-reported baseline of 0.739. We present a fine-grained error analysis showing that failures concentrate almost entirely in argument value formatting, including currency codes, ISO language codes, and transliteration, rather than in tool selection or task comprehension. These findings suggest that targeted fine-tuning or post-processing for structured-value normalization is a promising direction for improving Arabic function-calling performance. abjad aisa arabicfc.pdf %U https://aclanthology.org/2026.arabicnlp-sharedtasks.204/ %P 1585-1591
Markdown (Informal)
[Abjad at AISA-ArabicFC: Error Analysis and Prompt Engineering for Arabic Function Calling](https://aclanthology.org/2026.arabicnlp-sharedtasks.204/) (Lakab et al., ArabicNLP 2026)