@inproceedings{barmandah-etal-2026-namaa,
title = "{NAMAA} Community at {A}ra{G}enre 2026: From Encoder Baselines to Self-Consistent {LLM} Ensembling for Hierarchical {A}rabic Genre Classification",
author = "Barmandah, Hassan and
Elhosiny, Israa and
El-Ghawi, Yousra Alaa and
Nacar, Omer",
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.33/",
pages = "271--276",
ISBN = "979-8-89176-497-2",
abstract = "Hierarchical, definition-guided genre classification places a short Arabic text under a broad genre and, within it, a fine-grained specific genre, using only a natural-language definition of each. We present NAMAA{'}s submission to AraGenre 2026. Fine-tuned bi-encoder classifiers reached 0.93 hierarchical macro F1 on development via data augmentation and cross-lingual pretraining, but collapsed to as low as 0.22 on the released test set, having specialized to a hand-engineered definition style that missed the test set{'}s larger, 74-genre taxonomy. We root-caused this gap and switched to zero-shot LLM classification, matching the best fine-tuned ensemble{'}s test score (0.6899 hierarchical F1) with no training; layering self-consistency sampling and disagreement resolution raised this further to 0.7013, ranking 3rd of 18 teams. Specific Macro F1 (0.5114) lags well behind Broad Macro F1 (0.8913), showing that most remaining errors concentrate in fine-grained genre choices rather than broad-category mistakes. Zero-shot LLM prompting generalizes across this definition and taxonomy shift where fine-tuned, definition-conditioned encoders do not. We release our code and system resources to support reproducibility and further research.[{\ensuremath{<}}https://github.com/NAMAA-ORG/Aragenre-Definition-Guided-Genre{\ensuremath{>}}]."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="barmandah-etal-2026-namaa">
<titleInfo>
<title>NAMAA Community at AraGenre 2026: From Encoder Baselines to Self-Consistent LLM Ensembling for Hierarchical Arabic Genre Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Barmandah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Israa</namePart>
<namePart type="family">Elhosiny</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yousra</namePart>
<namePart type="given">Alaa</namePart>
<namePart type="family">El-Ghawi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Nacar</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>Hierarchical, definition-guided genre classification places a short Arabic text under a broad genre and, within it, a fine-grained specific genre, using only a natural-language definition of each. We present NAMAA’s submission to AraGenre 2026. Fine-tuned bi-encoder classifiers reached 0.93 hierarchical macro F1 on development via data augmentation and cross-lingual pretraining, but collapsed to as low as 0.22 on the released test set, having specialized to a hand-engineered definition style that missed the test set’s larger, 74-genre taxonomy. We root-caused this gap and switched to zero-shot LLM classification, matching the best fine-tuned ensemble’s test score (0.6899 hierarchical F1) with no training; layering self-consistency sampling and disagreement resolution raised this further to 0.7013, ranking 3rd of 18 teams. Specific Macro F1 (0.5114) lags well behind Broad Macro F1 (0.8913), showing that most remaining errors concentrate in fine-grained genre choices rather than broad-category mistakes. Zero-shot LLM prompting generalizes across this definition and taxonomy shift where fine-tuned, definition-conditioned encoders do not. We release our code and system resources to support reproducibility and further research.[\ensuremath<https://github.com/NAMAA-ORG/Aragenre-Definition-Guided-Genre\ensuremath>].</abstract>
<identifier type="citekey">barmandah-etal-2026-namaa</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.33/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>271</start>
<end>276</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NAMAA Community at AraGenre 2026: From Encoder Baselines to Self-Consistent LLM Ensembling for Hierarchical Arabic Genre Classification
%A Barmandah, Hassan
%A Elhosiny, Israa
%A El-Ghawi, Yousra Alaa
%A Nacar, Omer
%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 barmandah-etal-2026-namaa
%X Hierarchical, definition-guided genre classification places a short Arabic text under a broad genre and, within it, a fine-grained specific genre, using only a natural-language definition of each. We present NAMAA’s submission to AraGenre 2026. Fine-tuned bi-encoder classifiers reached 0.93 hierarchical macro F1 on development via data augmentation and cross-lingual pretraining, but collapsed to as low as 0.22 on the released test set, having specialized to a hand-engineered definition style that missed the test set’s larger, 74-genre taxonomy. We root-caused this gap and switched to zero-shot LLM classification, matching the best fine-tuned ensemble’s test score (0.6899 hierarchical F1) with no training; layering self-consistency sampling and disagreement resolution raised this further to 0.7013, ranking 3rd of 18 teams. Specific Macro F1 (0.5114) lags well behind Broad Macro F1 (0.8913), showing that most remaining errors concentrate in fine-grained genre choices rather than broad-category mistakes. Zero-shot LLM prompting generalizes across this definition and taxonomy shift where fine-tuned, definition-conditioned encoders do not. We release our code and system resources to support reproducibility and further research.[\ensuremath<https://github.com/NAMAA-ORG/Aragenre-Definition-Guided-Genre\ensuremath>].
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.33/
%P 271-276
Markdown (Informal)
[NAMAA Community at AraGenre 2026: From Encoder Baselines to Self-Consistent LLM Ensembling for Hierarchical Arabic Genre Classification](https://aclanthology.org/2026.arabicnlp-sharedtasks.33/) (Barmandah et al., ArabicNLP 2026)
ACL