@inproceedings{alqaeri-etal-2026-thakaa,
title = "Thakaa at {A}ra{G}enre 2026: Definition-Guided {LLM} Judging with Full-Taxonomy Agreement-Gated Correction for Hierarchical {A}rabic Genre Classification",
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.38/",
pages = "300--312",
ISBN = "979-8-89176-497-2",
abstract = "We report the first-place system in AraGenre 2026 (0.7352 Hierarchical Macro F1, 18 teams). The task assigns each of 27,972 hidden-test Arabic segments one of 6 broad and one of 74 specific genres, given only as English prose definitions, with the specific-label inventory disjoint from training. Our pipeline updates no model parameters but is not free of task-specific effort: the judge prompt carries 74 hand-written cues, and components were selected on the public leaderboard. A family-restricted, definition-guided LLM judge scores candidate genres setwise under a hierarchically constrained decoding scheme, whose five-step pipeline reaches 0.7139. That base led on Specific Macro F1 but trailed on Broad Macro F1, so we add a correction stage: two instruction models re-predict the specific genre, each shown the entire 74-definition taxonomy, and a label is edited only where both agree against the base. That system scores 0.892 Broad Macro F1, alongside fewer topic-trap calls, where the subject a text discusses displaces the genre it instantiates. In a post-evaluation audit of instances that the base labelled as book descriptions, Religious calls fall 394 {\textrightarrow} 233 {\textrightarrow} 119 as the prompt adds the type-versus-topic convention and then the full taxonomy. Refinements and an attractor drain reach 0.7352."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alqaeri-etal-2026-thakaa">
<titleInfo>
<title>Thakaa at AraGenre 2026: Definition-Guided LLM Judging with Full-Taxonomy Agreement-Gated Correction for Hierarchical Arabic Genre Classification</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>We report the first-place system in AraGenre 2026 (0.7352 Hierarchical Macro F1, 18 teams). The task assigns each of 27,972 hidden-test Arabic segments one of 6 broad and one of 74 specific genres, given only as English prose definitions, with the specific-label inventory disjoint from training. Our pipeline updates no model parameters but is not free of task-specific effort: the judge prompt carries 74 hand-written cues, and components were selected on the public leaderboard. A family-restricted, definition-guided LLM judge scores candidate genres setwise under a hierarchically constrained decoding scheme, whose five-step pipeline reaches 0.7139. That base led on Specific Macro F1 but trailed on Broad Macro F1, so we add a correction stage: two instruction models re-predict the specific genre, each shown the entire 74-definition taxonomy, and a label is edited only where both agree against the base. That system scores 0.892 Broad Macro F1, alongside fewer topic-trap calls, where the subject a text discusses displaces the genre it instantiates. In a post-evaluation audit of instances that the base labelled as book descriptions, Religious calls fall 394 → 233 → 119 as the prompt adds the type-versus-topic convention and then the full taxonomy. Refinements and an attractor drain reach 0.7352.</abstract>
<identifier type="citekey">alqaeri-etal-2026-thakaa</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.38/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>300</start>
<end>312</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Thakaa at AraGenre 2026: Definition-Guided LLM Judging with Full-Taxonomy Agreement-Gated Correction for Hierarchical Arabic Genre Classification
%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
%X We report the first-place system in AraGenre 2026 (0.7352 Hierarchical Macro F1, 18 teams). The task assigns each of 27,972 hidden-test Arabic segments one of 6 broad and one of 74 specific genres, given only as English prose definitions, with the specific-label inventory disjoint from training. Our pipeline updates no model parameters but is not free of task-specific effort: the judge prompt carries 74 hand-written cues, and components were selected on the public leaderboard. A family-restricted, definition-guided LLM judge scores candidate genres setwise under a hierarchically constrained decoding scheme, whose five-step pipeline reaches 0.7139. That base led on Specific Macro F1 but trailed on Broad Macro F1, so we add a correction stage: two instruction models re-predict the specific genre, each shown the entire 74-definition taxonomy, and a label is edited only where both agree against the base. That system scores 0.892 Broad Macro F1, alongside fewer topic-trap calls, where the subject a text discusses displaces the genre it instantiates. In a post-evaluation audit of instances that the base labelled as book descriptions, Religious calls fall 394 → 233 → 119 as the prompt adds the type-versus-topic convention and then the full taxonomy. Refinements and an attractor drain reach 0.7352.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.38/
%P 300-312
Markdown (Informal)
[Thakaa at AraGenre 2026: Definition-Guided LLM Judging with Full-Taxonomy Agreement-Gated Correction for Hierarchical Arabic Genre Classification](https://aclanthology.org/2026.arabicnlp-sharedtasks.38/) (Alqaeri et al., ArabicNLP 2026)
ACL