@inproceedings{dinh-van-2026-hp-aragenre,
title = "{HP} at {A}ra{G}enre 2026: {LLM}-Guided Pseudo-Labeling for Hierarchical {A}rabic Genre Classification with {MARBERT}",
author = "{\DJ}inh, Ho{\`a}ng Phong and
V{\u{a}}n, Th{\`i}n {\DJ}ặng",
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.29/",
pages = "252--256",
ISBN = "979-8-89176-497-2",
abstract = "This paper presents the system submitted by team HP for the AraGenre 2026 Shared Task on Hierarchical Definition-Guided Arabic Genre Classification. To address the low-resource constraint of the provided dataset (140 labeled training samples), we propose a two-stage pipeline combining LLM-based pseudo-labeling with supervised fine-tuning. In the first stage, we evaluate several models under a 5-fold cross-validation framework, including Gemini 3.5 Flash Lite (0.9413), Qwen2.5 7B (0.7203), LLaMA 3.1 8B (0.6380), and a multilingual NLI model (0.3099). Based on these results, Gemini 3.5 Flash Lite is selected to generate pseudo-labels for the unlabeled test set using a definition-guided few-shot prompt. In the second stage, MARBERTv2 and ARBERTv2 are fine-tuned on approximately 28,000 pseudo-labeled samples. Our experiments show that MARBERTv2 achieves the best standalone score of 0.7169 Hierarchical Macro F1, outperforming both ARBERTv2 (0.7118) and a soft voting ensemble (0.7165), suggesting that Arabic-specialized pretraining of MARBERTv2 is more effective than model ensembling for this task."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dinh-van-2026-hp-aragenre">
<titleInfo>
<title>HP at AraGenre 2026: LLM-Guided Pseudo-Labeling for Hierarchical Arabic Genre Classification with MARBERT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hoàng</namePart>
<namePart type="given">Phong</namePart>
<namePart type="family">Đinh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thìn</namePart>
<namePart type="given">Đặng</namePart>
<namePart type="family">Văn</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>This paper presents the system submitted by team HP for the AraGenre 2026 Shared Task on Hierarchical Definition-Guided Arabic Genre Classification. To address the low-resource constraint of the provided dataset (140 labeled training samples), we propose a two-stage pipeline combining LLM-based pseudo-labeling with supervised fine-tuning. In the first stage, we evaluate several models under a 5-fold cross-validation framework, including Gemini 3.5 Flash Lite (0.9413), Qwen2.5 7B (0.7203), LLaMA 3.1 8B (0.6380), and a multilingual NLI model (0.3099). Based on these results, Gemini 3.5 Flash Lite is selected to generate pseudo-labels for the unlabeled test set using a definition-guided few-shot prompt. In the second stage, MARBERTv2 and ARBERTv2 are fine-tuned on approximately 28,000 pseudo-labeled samples. Our experiments show that MARBERTv2 achieves the best standalone score of 0.7169 Hierarchical Macro F1, outperforming both ARBERTv2 (0.7118) and a soft voting ensemble (0.7165), suggesting that Arabic-specialized pretraining of MARBERTv2 is more effective than model ensembling for this task.</abstract>
<identifier type="citekey">dinh-van-2026-hp-aragenre</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.29/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>252</start>
<end>256</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HP at AraGenre 2026: LLM-Guided Pseudo-Labeling for Hierarchical Arabic Genre Classification with MARBERT
%A Đinh, Hoàng Phong
%A Văn, Thìn Đặng
%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 dinh-van-2026-hp-aragenre
%X This paper presents the system submitted by team HP for the AraGenre 2026 Shared Task on Hierarchical Definition-Guided Arabic Genre Classification. To address the low-resource constraint of the provided dataset (140 labeled training samples), we propose a two-stage pipeline combining LLM-based pseudo-labeling with supervised fine-tuning. In the first stage, we evaluate several models under a 5-fold cross-validation framework, including Gemini 3.5 Flash Lite (0.9413), Qwen2.5 7B (0.7203), LLaMA 3.1 8B (0.6380), and a multilingual NLI model (0.3099). Based on these results, Gemini 3.5 Flash Lite is selected to generate pseudo-labels for the unlabeled test set using a definition-guided few-shot prompt. In the second stage, MARBERTv2 and ARBERTv2 are fine-tuned on approximately 28,000 pseudo-labeled samples. Our experiments show that MARBERTv2 achieves the best standalone score of 0.7169 Hierarchical Macro F1, outperforming both ARBERTv2 (0.7118) and a soft voting ensemble (0.7165), suggesting that Arabic-specialized pretraining of MARBERTv2 is more effective than model ensembling for this task.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.29/
%P 252-256
Markdown (Informal)
[HP at AraGenre 2026: LLM-Guided Pseudo-Labeling for Hierarchical Arabic Genre Classification with MARBERT](https://aclanthology.org/2026.arabicnlp-sharedtasks.29/) (Đinh & Văn, ArabicNLP 2026)
ACL