@inproceedings{bostaty-etal-2026-wathiqteam,
title = "{W}athiq{T}eam at {A}ra{G}enre 2026: Class-Balanced Hybrid Retrieval with Selective {LLM} Reranking",
author = "Bostaty, Najat and
Almasri, Salam and
Al Shaabani, Bushra and
Alhossny, Raghad and
Sonbol, Riad",
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.37/",
pages = "295--299",
ISBN = "979-8-89176-497-2",
abstract = "We present WathiqTeam{'}s system for the AraGenre 2026 Shared Task on hierarchical Arabic genre classification. The task requires assigning each Arabic text both one of six broad genres and one of 74 fine-grained specific genres organised beneath them. This setting is particularly challenging because many specific genres overlap in topic and vocabulary, while the hierarchy is highly asymmetric: the six broad genres contain substantially different numbers of specific children. We address these challenges with a broad-first retrieval architecture. Multilingual E5 compares Arabic texts with English genre definitions, an Arabic sentence encoder retrieves generated Arabic prototypes, and BM25 preserves exact lexical and structural cues. At the broad level, class-balanced pooling prevents parents with larger prototype pools from receiving more votes. After hard hierarchical gating, Weighted Reciprocal Rank Fusion combines the three independent rankings for the remaining specific labels. Qwen3 reranks only uncertain top-two broad decisions and is constrained by internal ensemble support. The submitted system achieved 0.4559 Hierarchical Macro F1, with 0.6250 Broad Macro F1 and 0.2869 Specific Macro F1. Component-oriented official runs show that class balancing and level-specific fusion produced most of the gain, while selective LLM reranking provided a small final improvement."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bostaty-etal-2026-wathiqteam">
<titleInfo>
<title>WathiqTeam at AraGenre 2026: Class-Balanced Hybrid Retrieval with Selective LLM Reranking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Najat</namePart>
<namePart type="family">Bostaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Almasri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bushra</namePart>
<namePart type="family">Al Shaabani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raghad</namePart>
<namePart type="family">Alhossny</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riad</namePart>
<namePart type="family">Sonbol</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 present WathiqTeam’s system for the AraGenre 2026 Shared Task on hierarchical Arabic genre classification. The task requires assigning each Arabic text both one of six broad genres and one of 74 fine-grained specific genres organised beneath them. This setting is particularly challenging because many specific genres overlap in topic and vocabulary, while the hierarchy is highly asymmetric: the six broad genres contain substantially different numbers of specific children. We address these challenges with a broad-first retrieval architecture. Multilingual E5 compares Arabic texts with English genre definitions, an Arabic sentence encoder retrieves generated Arabic prototypes, and BM25 preserves exact lexical and structural cues. At the broad level, class-balanced pooling prevents parents with larger prototype pools from receiving more votes. After hard hierarchical gating, Weighted Reciprocal Rank Fusion combines the three independent rankings for the remaining specific labels. Qwen3 reranks only uncertain top-two broad decisions and is constrained by internal ensemble support. The submitted system achieved 0.4559 Hierarchical Macro F1, with 0.6250 Broad Macro F1 and 0.2869 Specific Macro F1. Component-oriented official runs show that class balancing and level-specific fusion produced most of the gain, while selective LLM reranking provided a small final improvement.</abstract>
<identifier type="citekey">bostaty-etal-2026-wathiqteam</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.37/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>295</start>
<end>299</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WathiqTeam at AraGenre 2026: Class-Balanced Hybrid Retrieval with Selective LLM Reranking
%A Bostaty, Najat
%A Almasri, Salam
%A Al Shaabani, Bushra
%A Alhossny, Raghad
%A Sonbol, Riad
%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 bostaty-etal-2026-wathiqteam
%X We present WathiqTeam’s system for the AraGenre 2026 Shared Task on hierarchical Arabic genre classification. The task requires assigning each Arabic text both one of six broad genres and one of 74 fine-grained specific genres organised beneath them. This setting is particularly challenging because many specific genres overlap in topic and vocabulary, while the hierarchy is highly asymmetric: the six broad genres contain substantially different numbers of specific children. We address these challenges with a broad-first retrieval architecture. Multilingual E5 compares Arabic texts with English genre definitions, an Arabic sentence encoder retrieves generated Arabic prototypes, and BM25 preserves exact lexical and structural cues. At the broad level, class-balanced pooling prevents parents with larger prototype pools from receiving more votes. After hard hierarchical gating, Weighted Reciprocal Rank Fusion combines the three independent rankings for the remaining specific labels. Qwen3 reranks only uncertain top-two broad decisions and is constrained by internal ensemble support. The submitted system achieved 0.4559 Hierarchical Macro F1, with 0.6250 Broad Macro F1 and 0.2869 Specific Macro F1. Component-oriented official runs show that class balancing and level-specific fusion produced most of the gain, while selective LLM reranking provided a small final improvement.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.37/
%P 295-299
Markdown (Informal)
[WathiqTeam at AraGenre 2026: Class-Balanced Hybrid Retrieval with Selective LLM Reranking](https://aclanthology.org/2026.arabicnlp-sharedtasks.37/) (Bostaty et al., ArabicNLP 2026)
ACL